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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate introductions or explanations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    appé
    -0.76
    Portály
    -0.73
    homonymie
    -0.72
    UnitTesting
    -0.71
     endregion
    -0.70
    Искәрмәләр
    -0.70
    Abitanti
    -0.70
    beiros
    -0.68
    jsii
    -0.67
    -0.67
    POSITIVE LOGITS
    Heres
    1.14
     heres
    1.08
     voici
    0.91
    Voici
    0.79
     Voici
    0.78
     ecco
    0.73
     here
    0.72
     şöyle
    0.70
    heres
    0.69
    Ecco
    0.66
    Act Density 0.071%

    No Known Activations