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

    Neuronpedia

    INDEX
    Explanations

    phrases related to direct interactions between individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "face-to-face" or variations of it indicating personal interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     exploits
    -0.65
     rewriting
    -0.65
     vari
    -0.65
     aborted
    -0.64
     references
    -0.63
     tuning
    -0.62
     supplemented
    -0.62
     overc
    -0.61
     modified
    -0.61
     upgr
    -0.60
    POSITIVE LOGITS
    prison
    1.05
    advertising
    1.03
    itiveness
    1.03
    peer
    1.03
    surface
    1.00
    tail
    0.98
    acqu
    0.97
    distance
    0.95
    mouth
    0.92
    be
    0.91
    Act Density 0.036%

    No Known Activations