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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating singularity or one-to-one relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    one followed by hyphen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dbach
    -0.58
    retudo
    -0.57
    eavour
    -0.53
    httphttps
    -0.52
    rubin
    -0.50
     CreateTagHelper
    -0.49
     navideña
    -0.49
     esercit
    -0.49
     Tatsache
    -0.49
     Zeiten
    -0.48
    POSITIVE LOGITS
    One
    0.79
     single
    0.79
     One
    0.78
     ONE
    0.78
    ワン
    0.72
     oneness
    0.71
     one
    0.71
    one
    0.68
    ONE
    0.65
     ワン
    0.64
    Act Density 0.010%

    No Known Activations