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

    Neuronpedia

    INDEX
    Explanations

    statements introducing examples

    oai_token-act-pair · gpt-3.5-turbo

    phrases that introduce examples or instances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ailability
    -0.67
    ements
    -0.66
     unlaw
    -0.65
    inventoryQuantity
    -0.65
    Deal
    -0.64
     fulfil
    -0.60
    sil
    -0.60
    iosity
    -0.57
    iership
    -0.57
     unification
    -0.56
    POSITIVE LOGITS
    :#
    0.86
     suppose
    0.86
    ,.
    0.69
    xon
    0.66
     imagine
    0.65
    oths
    0.64
    lihood
    0.63
     consider
    0.63
    ,
    0.62
    :
    0.61
    Act Density 0.026%

    No Known Activations