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

    Neuronpedia

    INDEX
    Explanations

    verbs related to decision-making and action

    oai_token-act-pair · gpt-3.5-turbo

    phrases and concepts related to legal matters and obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bool
    -0.74
    ãĤ¼ãĤ¦ãĤ¹
    -0.74
    roo
    -0.73
    inav
    -0.69
    imensional
    -0.69
    ondon
    -0.68
    ikan
    -0.67
    These
    -0.67
    chool
    -0.67
    ategories
    -0.65
    POSITIVE LOGITS
     the
    0.89
     its
    0.82
     several
    0.81
     subsequent
    0.79
     neighboring
    0.76
     adjoining
    0.74
     passers
    0.74
     Manafort
    0.73
     his
    0.72
     existing
    0.71
    Act Density 0.905%

    No Known Activations