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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social and political topics

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to social welfare and political activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.76
    mble
    -0.66
    pta
    -0.63
     proble
    -0.60
    together
    -0.59
     curv
    -0.58
     rul
    -0.54
    merce
    -0.54
     tiss
    -0.54
    inho
    -0.53
    POSITIVE LOGITS
    sylv
    0.59
    PAC
    0.58
    Cruz
    0.57
    Washington
    0.56
     Tillerson
    0.55
     ALEC
    0.55
     Conway
    0.54
    ashington
    0.54
     Ankara
    0.53
    cipled
    0.53
    Act Density 1.282%

    No Known Activations