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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political or ideological defection

    oai_token-act-pair · gpt-3.5-turbo

    terms related to political defections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hemp
    -0.74
     Lans
    -0.72
     Ducks
    -0.71
     Dice
    -0.71
    #$
    -0.68
    ãĥĥãĤ¯
    -0.64
     Carney
    -0.64
     #####
    -0.63
    zer
    -0.63
    frey
    -0.62
    POSITIVE LOGITS
    ighters
    0.88
    uese
    0.86
    ible
    0.80
    ibility
    0.78
    atile
    0.78
    iru
    0.75
    igent
    0.74
    itives
    0.74
    oidal
    0.73
    inally
    0.72
    Act Density 0.030%

    No Known Activations