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

    Neuronpedia

    INDEX
    Explanations

    phrases related to failure or the absence of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uire
    -0.16
    oplay
    -0.14
    óż
    -0.14
    eway
    -0.14
    ulkan
    -0.14
    ernen
    -0.13
    etri
    -0.13
    uzey
    -0.13
    oli
    -0.13
    _TAC
    -0.13
    POSITIVE LOGITS
     single
    0.45
    single
    0.39
     SINGLE
    0.39
    Single
    0.36
    -single
    0.35
     Single
    0.35
     einz
    0.31
     jedin
    0.30
    _single
    0.30
     iota
    0.30
    Act Density 0.251%

    No Known Activations