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

    Neuronpedia

    INDEX
    Explanations

    statements related to manual tasks or actions

    oai_token-act-pair · gpt-3.5-turbo

    references to manual actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.86
    addons
    -0.75
    iens
    -0.73
    rug
    -0.73
    soon
    -0.72
     Parables
    -0.71
    riots
    -0.71
     Sisters
    -0.68
    acious
    -0.68
     Coverage
    -0.68
    POSITIVE LOGITS
     exting
    0.89
     induct
    0.85
     override
    0.84
     operated
    0.83
     replen
    0.81
     configured
    0.80
     calibr
    0.80
    ©¶æ
    0.79
     overcl
    0.79
     controlled
    0.78
    Act Density 0.014%

    No Known Activations