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

    Neuronpedia

    INDEX
    Explanations

    references to file attachments in documents

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     suspended
    -0.73
     DPM
    -0.73
     suspendu
    -0.71
     suspend
    -0.68
     Kers
    -0.66
    
    -0.66
     suspensions
    -0.65
    -0.65
     hanging
    -0.64
     suspending
    -0.64
    POSITIVE LOGITS
    tahui
    0.91
    InSection
    0.89
     utafitiHapana
    0.82
    Petr
    0.79
     Pratt
    0.76
     relâche
    0.76
     Petr
    0.74
    Holt
    0.72
    ufact
    0.71
    HtmlAttribute
    0.71
    Act Density 0.007%

    No Known Activations