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

    Neuronpedia

    INDEX
    Explanations

    phrases related to making judgments or calls to action

    oai_token-act-pair · gpt-3.5-turbo

    references to judgment and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    KC
    -0.80
    aceae
    -0.77
    TPP
    -0.75
    heny
    -0.73
    FORMATION
    -0.72
    href
    -0.71
    TERN
    -0.71
    ubric
    -0.70
    atten
    -0.68
    ieri
    -0.66
    POSITIVE LOGITS
     judgement
    1.34
     judgment
    1.31
     judgments
    1.16
     Judgment
    0.99
    jud
    0.92
     jud
    0.92
    eering
    0.89
     verdict
    0.84
    al
    0.83
     judging
    0.81
    Act Density 0.032%

    No Known Activations