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

    Neuronpedia

    INDEX
    Explanations

    elements related to aspiration for improvement and change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fubject
    -0.83
     houſe
    -0.77
     ſtate
    -0.76
     purpoſe
    -0.75
     poffe
    -0.68
     whoſe
    -0.67
     beſt
    -0.67
     ſche
    -0.66
     endregion
    -0.66
     greateſt
    -0.66
    POSITIVE LOGITS
     plenty
    0.62
    IsMutable
    0.62
    LabelTagHelper
    0.61
     rhestr
    0.59
    SequentialGroup
    0.58
    ReusableCell
    0.55
    aterin
    0.53
    adpleegd
    0.52
     loads
    0.51
     lots
    0.51
    Act Density 0.522%

    No Known Activations