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

    Neuronpedia

    INDEX
    Explanations

    phrases related to relationships and interactions between individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to interpersonal relationships and connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    veyard
    -0.60
    letters
    -0.58
    renheit
    -0.58
    oute
    -0.57
    models
    -0.56
    gur
    -0.55
     balloons
    -0.55
     nowhere
    -0.55
    tops
    -0.54
     Stories
    -0.54
    POSITIVE LOGITS
    other
    1.13
     successive
    0.97
     individually
    0.90
     iteration
    0.88
     respective
    0.82
    dimension
    0.79
     other
    0.79
     individual
    0.78
    ones
    0.77
     person
    0.77
    Act Density 0.039%

    No Known Activations