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

    Neuronpedia

    INDEX
    Explanations

    references to willingness to join or contribute to an organization or group

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing a desire or intention to belong or contribute to a group or organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ceilings
    -0.76
    gently
    -0.74
     torped
    -0.67
    berus
    -0.67
     toddlers
    -0.66
     patterns
    -0.62
     infants
    -0.60
     calves
    -0.60
     casc
    -0.60
    culosis
    -0.59
    POSITIVE LOGITS
    aking
    0.86
    icle
    0.81
    ridge
    0.80
    ner
    0.78
    ioned
    0.77
    raction
    0.77
    thing
    0.77
    icular
    0.75
    lass
    0.73
    ICLE
    0.73
    Act Density 0.032%

    No Known Activations