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

    Neuronpedia

    INDEX
    Explanations

    phrases related to one-on-one interactions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "one-on-one."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thin
    -0.64
     tongues
    -0.62
     Narr
    -0.61
     equ
    -0.57
    wings
    -0.57
    avanaugh
    -0.56
    cair
    -0.56
     newsletters
    -0.55
     dred
    -0.55
     forks
    -0.54
    POSITIVE LOGITS
    etime
    0.77
    itability
    0.76
    iversal
    0.73
    apest
    0.73
    clusive
    0.68
    odge
    0.63
    heat
    0.63
    etimes
    0.62
    ĪĴ
    0.60
    ulton
    0.59
    Act Density 0.060%

    No Known Activations