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

    Neuronpedia

    INDEX
    Explanations

    words related to interaction and engaging with other entities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "interact" and its variations, indicating a focus on interaction and interactivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cott
    -0.73
    peria
    -0.69
    zn
    -0.67
     Bav
    -0.66
    ciples
    -0.63
    corn
    -0.62
    GE
    -0.61
    DER
    -0.61
    crow
    -0.59
    conservancy
    -0.59
    POSITIVE LOGITS
    ivity
    1.22
    ively
    1.02
    uate
    1.01
    ivating
    0.97
    ually
    0.94
    uating
    0.91
    uates
    0.90
    uated
    0.90
    ivated
    0.89
    iveness
    0.89
    Act Density 0.036%

    No Known Activations