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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe the context or conditions of an action

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    umenti
    -0.78
    asantry
    -0.75
     Normdatei
    -0.74
    cellona
    -0.73
     Cardona
    -0.73
    enium
    -0.72
    ه
    -0.72
    nappropriate
    -0.71
     referrerpolicy
    -0.71
    croix
    -0.71
    POSITIVE LOGITS
    theless
    0.94
    withstanding
    0.92
    ostante
    0.82
    teen
    0.74
    fraid
    0.71
    depend
    0.71
    adays
    0.65
    
    0.65
    where
    0.64
    queryInterface
    0.63
    Act Density 0.230%

    No Known Activations