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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate future intentions or plans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -0.95
     Nestor
    -0.86
     zelve
    -0.81
    \{\\
    -0.80
     HasFactory
    -0.80
    ſelves
    -0.80
     InputDecoration
    -0.80
    rsiniz
    -0.79
     ASE
    -0.77
    حوالہ
    -0.77
    POSITIVE LOGITS
     gonna
    1.19
     Gonna
    1.19
    Gonna
    1.12
     GONNA
    1.10
    gonna
    1.01
     will
    0.84
     want
    0.79
     be
    0.78
     wanna
    0.76
     WILL
    0.75
    Act Density 0.067%

    No Known Activations