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

    Neuronpedia

    INDEX
    Explanations

    phrases that suggest conditions or caveats related to statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.63
    rungsseite
    -0.55
    thâu
    -0.54
     للاسماء
    -0.53
    tagHelperRunner
    -0.52
    verwijspagina
    -0.51
    BufferException
    -0.47
     estekak
    -0.47
     يتيمه
    -0.46
    OGND
    -0.46
    POSITIVE LOGITS
    Regarding
    0.77
     Concerning
    0.74
     Regarding
    0.72
    Concerning
    0.71
    至于
    0.70
    至於
    0.64
     regarding
    0.60
     concerning
    0.58
     respecto
    0.55
     mengenai
    0.54
    Act Density 0.287%

    No Known Activations