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

    Neuronpedia

    INDEX
    Explanations

    conditional statements or phrases indicating hypothetical situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaf
    -0.72
     Parkes
    -0.72
    Obrázky
    -0.71
     pleaſure
    -0.70
     Şi
    -0.68
     Eſ
    -0.67
     anſ
    -0.66
     ſte
    -0.66
     ejus
    -0.65
     Rima
    -0.65
    POSITIVE LOGITS
     jakby
    0.84
     seolah
    0.72
    >{@
    0.72
     будто
    0.71
     словно
    0.65
     ivelany
    0.63
     gdyby
    0.59
    principalTable
    0.58
     if
    0.58
    AddTagHelper
    0.58
    Act Density 0.103%

    No Known Activations