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

    Neuronpedia

    INDEX
    Explanations

    verbs related to movement or action directed towards a specific goal or location

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "enter" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    killer
    -0.71
    zbollah
    -0.67
    cks
    -0.64
    gnu
    -0.62
    okia
    -0.62
    bara
    -0.62
    plement
    -0.62
    cussion
    -0.62
    copy
    -0.60
    esa
    -0.60
    POSITIVE LOGITS
    prising
    1.25
    prise
    1.02
    prises
    0.99
    tain
    0.87
    TAIN
    0.87
     INTO
    0.85
     into
    0.80
    tainment
    0.80
     adulthood
    0.79
     unch
    0.75
    Act Density 0.038%

    No Known Activations