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

    Neuronpedia

    INDEX
    Explanations

    verbs related to participation or involvement

    oai_token-act-pair · gpt-3.5-turbo

    the word "engage" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etry
    -0.76
    bey
    -0.68
    issue
    -0.65
    Origin
    -0.63
    opers
    -0.62
    pled
    -0.62
    ological
    -0.62
     Printed
    -0.61
    fer
    -0.61
     ported
    -0.60
    POSITIVE LOGITS
    ments
    0.91
     engaged
    0.88
    TAIN
    0.88
    ienced
    0.84
    lished
    0.84
     engagement
    0.76
    ENC
    0.75
    reement
    0.73
    aeper
    0.73
    encer
    0.71
    Act Density 0.016%

    No Known Activations