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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "clear" followed by a number (e.g., "clear 10")

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating clarity or obviousness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tremend
    -0.95
    inse
    -0.77
    uld
    -0.77
     Loft
    -0.76
    ITAL
    -0.75
    FactoryReloaded
    -0.69
    eatures
    -0.69
     arrog
    -0.67
     nostalg
    -0.66
     destro
    -0.66
    POSITIVE LOGITS
    ances
    1.26
    cut
    1.16
    ance
    0.97
    cuts
    0.94
    headed
    0.93
    iary
    0.91
     indication
    0.89
    cutting
    0.85
     sailing
    0.84
     deline
    0.81
    Act Density 0.045%

    No Known Activations