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

    Neuronpedia

    INDEX
    Explanations

    connections or transitions in narrative or explanatory sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Harlow
    -0.78
     Irm
    -0.78
    ();)
    -0.72
     Winfrey
    -0.72
     Efq
    -0.72
    ilíbrio
    -0.71
    checkNotNull
    -0.70
    randomUUID
    -0.69
     himſelf
    -0.69
     fap
    -0.69
    POSITIVE LOGITS
     THEN
    0.90
     then
    0.88
    THEN
    0.85
     Then
    0.84
     Dann
    0.79
    Then
    0.74
    then
    0.74
    vdash
    0.73
     gynhyrchwyd
    0.73
     entonces
    0.70
    Act Density 0.111%

    No Known Activations