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

    Neuronpedia

    INDEX
    Explanations

    rough drafts of documents

    oai_token-act-pair · gpt-3.5-turbo

    numerical expressions or values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pastoral
    -0.76
    Tes
    -0.72
     convict
    -0.70
    intend
    -0.67
     respons
    -0.66
     ped
    -0.65
    alach
    -0.63
     tract
    -0.62
     pri
    -0.60
    achus
    -0.59
    POSITIVE LOGITS
     Languages
    0.85
     Explicit
    0.81
    argo
    0.72
     Requirements
    0.72
    hew
    0.72
     Lastly
    0.71
    redits
    0.70
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    0.69
    anguages
    0.69
    ï¸ı
    0.69
    Act Density 0.041%

    No Known Activations