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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating hypothetical situations or conditional statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    يكب
    -0.69
     Conci
    -0.66
     "..\..\..\
    -0.65
    enumii
    -0.65
    Jîn
    -0.65
    cephala
    -0.64
    rshire
    -0.64
    richTextPanel
    -0.63
     Maguire
    -0.63
    verwijspagina
    -0.61
    POSITIVE LOGITS
    ULD
    0.71
    Would
    0.67
     likely
    0.67
     fain
    0.66
     ordinarily
    0.64
     typically
    0.62
     behö
    0.60
     normally
    0.59
     WOULD
    0.59
     certainly
    0.59
    Act Density 0.130%

    No Known Activations