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

    Neuronpedia

    INDEX
    Explanations

    mentions of proposals or suggested actions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of proposals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wood
    -0.77
    vin
    -0.73
    iliate
    -0.72
    nie
    -0.69
    zona
    -0.66
    si
    -0.66
    san
    -0.66
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.65
    burn
    -0.65
    bourne
    -0.65
    POSITIVE LOGITS
     proposals
    0.99
     proposal
    0.90
     proposing
    0.85
     proposed
    0.76
     decriminal
    0.74
    ļéĨĴ
    0.70
     proposes
    0.69
     moot
    0.66
    xual
    0.66
     unveiled
    0.65
    Act Density 0.026%

    No Known Activations