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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating outcomes or conclusions drawn from evidence or analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Jereo
    -0.60
    LLocation
    -0.59
    styleUrls
    -0.57
     CURIAM
    -0.55
    ^(@)
    -0.53
    EnableWeb
    -0.52
    aaral
    -0.52
    ialak
    -0.50
    JNIEnv
    -0.49
    SharedDtor
    -0.49
    POSITIVE LOGITS
    EndContext
    0.69
     resultó
    0.68
     subsequently
    0.63
    果然
    0.63
     fortunately
    0.62
     heure
    0.61
    binant
    0.61
    addGap
    0.60
     allait
    0.60
    結果
    0.59
    Act Density 0.385%

    No Known Activations