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

    Neuronpedia

    INDEX
    Explanations

    expressions related to evaluations and opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    untas
    -0.17
    icken
    -0.16
    iedo
    -0.16
    arten
    -0.16
    vido
    -0.15
    ousel
    -0.15
    soft
    -0.14
    pill
    -0.14
    dete
    -0.13
    å·¥
    -0.13
    POSITIVE LOGITS
    osh
    0.15
    elsen
    0.15
    anager
    0.15
    æļ®
    0.15
    ittings
    0.14
    æµ´
    0.14
    Tro
    0.14
    @example
    0.14
    íķij
    0.14
    itionally
    0.13
    Act Density 0.480%

    No Known Activations