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

    Neuronpedia

    INDEX
    Explanations

    adjectives that describe adherence or compliance

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to adherence and submission to various principles or beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pelling
    -0.63
    UFF
    -0.56
    boarding
    -0.53
    picking
    -0.51
     digging
    -0.50
     sighting
    -0.49
    overs
    -0.49
    ierra
    -0.47
     stalking
    -0.47
    seen
    -0.47
    POSITIVE LOGITS
     thereto
    1.02
     to
    0.95
     unto
    0.83
     nostalg
    0.82
     solely
    0.81
     strictly
    0.78
    aciously
    0.78
     exclusively
    0.77
    antly
    0.75
    ingly
    0.74
    Act Density 0.137%

    No Known Activations