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

    Neuronpedia

    INDEX
    Explanations

    phrases that are emphasized or highlighted within the text

    oai_token-act-pair · gpt-3.5-turbo

    expressions of hopes and fears related to personal and familial situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ½
    -0.74
     purs
    -0.72
    argon
    -0.72
    cius
    -0.68
    glers
    -0.66
    zin
    -0.65
     Candidate
    -0.65
    oga
    -0.64
    agon
    -0.63
    obar
    -0.62
    POSITIVE LOGITS
    Scroll
    1.03
    SPONSORED
    0.86
    Speaking
    0.80
    Actor
    0.78
    However
    0.77
    Shape
    0.74
    Yesterday
    0.74
    Scotland
    0.73
    Hundreds
    0.72
    Prof
    0.72
    Act Density 0.446%

    No Known Activations