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

    Neuronpedia

    INDEX
    Explanations

    contradictory statements

    oai_token-act-pair · gpt-3.5-turbo

    expressions of uncertainty or ambiguity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    senal
    -0.85
     eleph
    -0.78
     subur
    -0.68
     exting
    -0.65
     activ
    -0.63
    ounter
    -0.63
    anmar
    -0.62
    inav
    -0.61
     pione
    -0.60
    ò
    -0.60
    POSITIVE LOGITS
     caveats
    0.90
     editors
    0.75
     Krugman
    0.75
     paraph
    0.75
     reader
    0.75
     nonetheless
    0.75
     commenters
    0.74
     apologies
    0.74
     readers
    0.74
     Slate
    0.73
    Act Density 1.327%

    No Known Activations