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

    Neuronpedia

    INDEX
    Explanations

    terms related to offenders and offending behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    اÙĬÙĨ
    -0.16
     Propel
    -0.16
    ëĭĪìķĦ
    -0.16
    MAS
    -0.16
    Mas
    -0.15
     Mas
    -0.15
    resh
    -0.15
    etti
    -0.14
    fait
    -0.14
    .fn
    -0.14
    POSITIVE LOGITS
    rana
    0.17
    ischer
    0.15
    çª
    0.14
    chan
    0.14
    h
    0.14
    ickers
    0.14
    ucid
    0.13
    orge
    0.13
    nap
    0.13
    rite
    0.13
    Act Density 0.007%

    No Known Activations