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

    Neuronpedia

    INDEX
    Explanations

    email-related actions such as "Close"

    oai_token-act-pair · gpt-3.5-turbo

    references to votes or voting processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thumbnails
    -0.84
    Catal
    -0.84
    女
    -0.83
    MAT
    -0.73
    Struct
    -0.73
    Translation
    -0.73
    Gene
    -0.70
    Sa
    -0.67
    Attempt
    -0.67
    Vari
    -0.65
    POSITIVE LOGITS
    resy
    0.80
     Trooper
    0.70
    angering
    0.65
    rophe
    0.63
    itars
    0.63
     retaliation
    0.62
    akening
    0.61
    rupt
    0.61
    licks
    0.60
    hitting
    0.60
    Act Density 0.000%

    No Known Activations