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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing commitment

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "commitment"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adish
    -0.73
    dos
    -0.67
    avis
    -0.65
     Caucas
    -0.65
    phe
    -0.65
    isen
    -0.64
    bin
    -0.64
    rors
    -0.62
    walking
    -0.61
    ox
    -0.61
    POSITIVE LOGITS
     commitment
    1.14
     commitments
    0.94
     Commit
    0.86
     allegiance
    0.83
    irmation
    0.82
    ilitary
    0.76
     pledge
    0.74
    gence
    0.74
    commit
    0.73
    xual
    0.71
    Act Density 0.014%

    No Known Activations