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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating sufficiency or proof in mathematical contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    InputBorder
    -0.74
    }))
    -0.72
     ChromeDriver
    -0.63
    StoryboardSegue
    -0.62
    middels
    -0.61
    }));
    -0.59
     Induced
    -0.59
    Modifications
    -0.59
    formik
    -0.58
    pendente
    -0.57
    POSITIVE LOGITS
     насељу
    0.55
     TextAppearance
    0.55
    ;#
    0.52
    ovsk
    0.50
    poder
    0.49
    viens
    0.49
    argli
    0.49
     hjer
    0.48
     Buche
    0.48
     Byers
    0.48
    Act Density 0.005%

    No Known Activations