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

    Neuronpedia

    INDEX
    Explanations

    phrases related to meeting or encountering people

    oai_token-act-pair · gpt-3.5-turbo

    references to relationships and personal connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ACTIONS
    -0.67
     untreated
    -0.65
    ĸļ
    -0.64
     subp
    -0.63
    forcing
    -0.62
    uploads
    -0.59
    icide
    -0.58
     collects
    -0.58
     exerted
    -0.58
    icides
    -0.57
    POSITIVE LOGITS
    tle
    1.01
    lyak
    0.83
     halfway
    0.83
    amorph
    0.75
    rises
    0.71
    zb
    0.71
    ritic
    0.70
     criteria
    0.70
     gaze
    0.68
     expectations
    0.68
    Act Density 0.116%

    No Known Activations