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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "enter" or its variations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "enter" and its various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    killer
    -0.63
    die
    -0.58
    cks
    -0.58
    gnu
    -0.58
    fml
    -0.58
     backdrop
    -0.57
    ector
    -0.57
    iane
    -0.57
     Archangel
    -0.57
    bara
    -0.57
    POSITIVE LOGITS
    prising
    1.41
    prise
    1.12
    prises
    1.11
    tain
    1.04
    TAIN
    0.97
    tainment
    0.95
     INTO
    0.94
     into
    0.94
    tained
    0.91
    taining
    0.87
    Act Density 0.040%

    No Known Activations