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

    Neuronpedia

    INDEX
    Explanations

    words related to legal and contractual obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     beginnetje
    -1.05
    DebuggerStep
    -0.96
     defaultstate
    -0.95
     betweenstory
    -0.91
     itſelf
    -0.89
    expandindo
    -0.86
     themſelves
    -0.85
     Jefus
    -0.84
     himſelf
    -0.83
     pleaſure
    -0.83
    POSITIVE LOGITS
     a
    0.55
     ve
    0.51
     the
    0.48
     an
    0.46
     "
    0.46
     
    0.44
     that
    0.43
     bộ
    0.41
     those
    0.41
     самого
    0.40
    Act Density 0.891%

    No Known Activations