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

    Neuronpedia

    INDEX
    Explanations

    phrases related to emotional states and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     probably
    -0.87
    probably
    -0.87
    Probably
    -0.85
     Probably
    -0.84
    almost
    -0.78
    Almost
    -0.76
    meist
    -0.73
     probabilmente
    -0.70
    Casi
    -0.69
     prolly
    -0.68
    POSITIVE LOGITS
     any
    1.08
     quelconque
    1.02
     yoksa
    0.95
    有任何
    0.92
     sufficiently
    0.88
    ใด
    0.88
     slightest
    0.87
     anything
    0.86
     ANY
    0.84
     jemals
    0.81
    Act Density 0.524%

    No Known Activations