Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instances where someone is possessing or owning something and giving information about past actions or events

    oai_token-act-pair · gpt-3.5-turbo

    instances of specific individuals and their involvement in meetings or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dimin
    -0.70
     differentiation
    -0.68
    Asset
    -0.64
     shrinking
    -0.61
     classification
    -0.60
    Sense
    -0.59
     tradem
    -0.58
     differentiate
    -0.58
     ambiguity
    -0.57
     obscurity
    -0.57
    POSITIVE LOGITS
     undertook
    1.25
     conducted
    1.08
     undertake
    1.06
     undertaken
    1.04
     initiated
    1.03
     performed
    0.96
     participated
    0.94
     attended
    0.92
     underwent
    0.90
     orchestrated
    0.89
    Act Density 0.131%

    No Known Activations