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

    Neuronpedia

    INDEX
    Explanations

    verbs related to the consequences of actions

    oai_token-act-pair · gpt-3.5-turbo

    words related to legal consequences or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pedia
    -0.72
     Accountability
    -0.60
    antry
    -0.58
     Roof
    -0.57
    yp
    -0.57
    Beer
    -0.56
    ACP
    -0.54
    Hom
    -0.54
     Carney
    -0.53
     unsupported
    -0.53
    POSITIVE LOGITS
    ues
    1.13
     ens
    1.07
    ilage
    1.04
    ue
    0.97
    ued
    0.97
    uers
    0.95
    oing
    0.86
    uing
    0.86
    uer
    0.82
    ailed
    0.81
    Act Density 0.036%

    No Known Activations