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

    Neuronpedia

    INDEX
    Explanations

    phrases involving the future tense or plans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -1.03
     InputDecoration
    -0.96
    ThroughAttribute
    -0.88
     tartalomajánló
    -0.83
    rsiniz
    -0.82
    ſelves
    -0.81
     Nestor
    -0.79
     pleaſure
    -0.77
     houſe
    -0.77
     HasFactory
    -0.76
    POSITIVE LOGITS
     gonna
    1.08
     Gonna
    1.05
    Gonna
    1.00
     GONNA
    0.96
     be
    0.88
    gonna
    0.80
     will
    0.78
     Will
    0.72
    getParam
    0.72
     WILL
    0.71
    Act Density 0.064%

    No Known Activations