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

    Neuronpedia

    INDEX
    Explanations

    phrases related to making choices or decisions

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "in favor of" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    falls
    -0.81
    quartered
    -0.75
    quarters
    -0.67
    forge
    -0.64
     describ
    -0.63
    venants
    -0.63
     hesitated
    -0.62
    mot
    -0.62
    abouts
    -0.61
     hesitate
    -0.60
    POSITIVE LOGITS
    WARD
    0.81
    aging
    0.72
    umbn
    0.70
    geries
    0.67
     preserving
    0.63
     recess
    0.63
     sake
    0.62
    onement
    0.62
    ãĤ¯
    0.62
     keeping
    0.60
    Act Density 0.090%

    No Known Activations