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

    Neuronpedia

    INDEX
    Explanations

    acts of kindness and charitable gestures

    oai_token-act-pair · gpt-3.5-turbo

    references to generosity and altruism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bam
    -0.73
     Showdown
    -0.69
     Ys
    -0.69
    fund
    -0.67
    INGTON
    -0.66
    ciation
    -0.65
     Sphere
    -0.64
     Milky
    -0.64
     ASAP
    -0.63
     Kob
    -0.61
    POSITIVE LOGITS
    ttes
    0.84
    depending
    0.82
    pas
    0.79
    times
    0.74
    oots
    0.73
    entimes
    0.71
    enos
    0.70
     incorrectly
    0.70
    pmwiki
    0.70
     underestimated
    0.68
    Act Density 0.450%

    No Known Activations