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

    Neuronpedia

    INDEX
    Explanations

    text related to the certainty or emphasis on a statement

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal feelings and opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Coffin
    -0.69
    illac
    -0.68
    chieve
    -0.66
     Femin
    -0.66
     Alban
    -0.66
    %:
    -0.65
    ousy
    -0.64
    achev
    -0.63
     Achieve
    -0.62
    dylib
    -0.60
    POSITIVE LOGITS
     accordingly
    0.73
    iol
    0.65
    Correct
    0.64
    bane
    0.64
     naturally
    0.64
     hopefully
    0.64
     externalToEVAOnly
    0.63
     definitely
    0.62
    initely
    0.62
     kinda
    0.61
    Act Density 0.841%

    No Known Activations