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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Over" signaling the start of a new piece of text or section

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Over" followed by numerical expressions of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arium
    -0.71
    ittal
    -0.66
    BILITY
    -0.65
    ILY
    -0.64
     preferably
    -0.64
    illary
    -0.64
    bernatorial
    -0.61
    udes
    -0.61
    ":[
    -0.60
     hereafter
    -0.60
    POSITIVE LOGITS
    whelming
    1.07
    lap
    1.04
    whel
    0.97
    lying
    0.95
    statement
    0.92
    hang
    0.92
    tones
    0.92
    valued
    0.92
    lander
    0.92
    lay
    0.92
    Act Density 0.030%

    No Known Activations