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

    Neuronpedia

    INDEX
    Explanations

    phrases that denote options or alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ddelweddau
    -0.70
    참고
    -0.63
     мѣ
    -0.60
    ónde
    -0.53
    TestBed
    -0.52
     perle
    -0.52
    ukunft
    -0.52
    存于互联网档案馆
    -0.51
     @"/
    -0.51
    LookAnd
    -0.51
    POSITIVE LOGITS
     either
    0.99
     Either
    0.88
    either
    0.87
    Either
    0.87
     or
    0.75
     либо
    0.73
    
    0.71
    ITHER
    0.71
     entweder
    0.70
     cualquiera
    0.67
    Act Density 0.336%

    No Known Activations