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

    Neuronpedia

    INDEX
    Explanations

    references to investigations related to political figures and potential misconduct

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lay
    -0.38
    b
    -0.34
     k
    -0.32
     private
    -0.31
     reposo
    -0.31
     διά
    -0.30
     beckon
    -0.30
    private
    -0.30
     fresh
    -0.29
     urma
    -0.29
    POSITIVE LOGITS
     pleaſure
    0.75
     juſ
    0.67
     myſelf
    0.64
     betweenstory
    0.62
    󠀠
    0.61
     Anſ
    0.60
     purpoſe
    0.60
     ſch
    0.59
    Manbalar
    0.59
     preſent
    0.59
    Act Density 0.074%

    No Known Activations