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

    Neuronpedia

    INDEX
    Explanations

    numbers related to quantities or measurements

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics and quantities related to population and time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Notice
    -0.66
    Go
    -0.64
     behavi
    -0.63
    uba
    -0.61
    Prom
    -0.60
    KO
    -0.58
    thia
    -0.58
     srfAttach
    -0.57
     unsus
    -0.57
     Warning
    -0.57
    POSITIVE LOGITS
    ottest
    0.84
    iest
    0.82
    hest
    0.80
    liest
    0.77
    esson
    0.69
    same
    0.68
    renches
    0.67
    gun
    0.65
    osphere
    0.64
    ollar
    0.64
    Act Density 0.264%

    No Known Activations