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

    Neuronpedia

    INDEX
    Explanations

    mentions and references to the word "one"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    θα
    -0.68
    hematical
    -0.67
    erle
    -0.66
    }';
    -0.66
     iconFacebook
    -0.65
     ―――――
    -0.64
    벡터
    -0.64
     >=",
    -0.62
    leſs
    -0.62
     raiſ
    -0.62
    POSITIVE LOGITS
     ones
    1.19
     Ones
    0.98
    Ones
    0.84
    WindowConstants
    0.82
    bootstrapcdn
    0.78
     satunya
    0.72
     it
    0.70
     ours
    0.66
    InitVars
    0.63
    ьаж
    0.63
    Act Density 0.084%

    No Known Activations