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

    Neuronpedia

    INDEX
    Explanations

    phrases involving future intentions or plans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :✨
    -0.85
     Italijanski
    -0.82
    حوالہ
    -0.72
    IsMutable
    -0.71
    AndEndTag
    -0.68
     Fides
    -0.67
    PreferredItem
    -0.67
    NameInMap
    -0.66
    ⓧ
    -0.66
     parseFrom
    -0.65
    POSITIVE LOGITS
     supposed
    0.90
     to
    0.89
     going
    0.88
     gonna
    0.87
     Gonna
    0.82
    supposed
    0.79
    Gonna
    0.76
     ought
    0.73
     GONNA
    0.72
     Going
    0.72
    Act Density 0.081%

    No Known Activations