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

    Neuronpedia

    INDEX
    Explanations

    phrases related to policies or actions being eliminated or discontinued

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of abolition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PAR
    -0.67
    PE
    -0.66
    Gate
    -0.63
     Ps
    -0.63
     Gaia
    -0.62
     Solitaire
    -0.62
    Downloadha
    -0.62
     Blizz
    -0.60
     Goo
    -0.59
    Rush
    -0.58
    POSITIVE LOGITS
     abolition
    1.08
    ©¶æ¥µ
    0.93
     abolish
    0.92
     abol
    0.85
     abolished
    0.85
     slavery
    0.84
    tarians
    0.83
    ntil
    0.78
    tarian
    0.74
    olition
    0.73
    Act Density 0.010%

    No Known Activations