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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "recover" and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HtmlAttribute
    -0.78
    ValueStyle
    -0.73
    utenants
    -0.71
    帖最后由
    -0.69
    TargetException
    -0.66
     getItemCount
    -0.66
     trajets
    -0.66
    ensement
    -0.64
    Denn
    -0.64
     BoxFit
    -0.63
    POSITIVE LOGITS
     recover
    1.14
     recovery
    1.03
     Recovery
    0.88
     Recover
    0.85
     recovers
    0.85
    recovery
    0.85
    Views
    0.82
     recovered
    0.78
     recovering
    0.78
    Recovery
    0.77
    Act Density 0.188%

    No Known Activations