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

    Neuronpedia

    INDEX
    Explanations

    phrases that specify precise details or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Controllo
    -0.82
     فريبيس
    -0.71
     <<<<<<<<<<<<<<
    -0.69
    Autoritní
    -0.69
     referenties
    -0.69
     laminate
    -0.67
    ModelForm
    -0.66
     يتيمه
    -0.65
     Diener
    -0.65
    Collegamenti
    -0.64
    POSITIVE LOGITS
     exactly
    1.87
    exactly
    1.80
     Exactly
    1.79
     exact
    1.79
    Exactly
    1.69
     Exact
    1.62
     EXACTLY
    1.60
     EXACT
    1.59
    Exact
    1.55
    exact
    1.52
    Act Density 0.082%

    No Known Activations