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

    Neuronpedia

    INDEX
    Explanations

    references to changes and upcoming events in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ñĩай
    -0.16
    ervas
    -0.16
    osten
    -0.15
    rowad
    -0.15
    iston
    -0.13
    465
    -0.13
    aversable
    -0.13
    utt
    -0.13
    encent
    -0.13
    ιβ
    -0.13
    POSITIVE LOGITS
     coming
    0.44
     Coming
    0.39
    Coming
    0.38
    coming
    0.38
     incoming
    0.34
     Incoming
    0.30
     forthcoming
    0.28
    Incoming
    0.28
     imminent
    0.26
     inbound
    0.25
    Act Density 0.071%

    No Known Activations