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

    Neuronpedia

    INDEX
    Explanations

    quoted phrases and expressions that convey approval or affirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    warf
    -0.18
    OUCH
    -0.16
    ï¼Ĩ
    -0.15
    触
    -0.15
    ctest
    -0.15
    )did
    -0.14
    addtogroup
    -0.14
    ëį°ìĿ´íĬ¸
    -0.14
     Formats
    -0.14
    haft
    -0.14
    POSITIVE LOGITS
    kla
    0.16
    858
    0.15
     Shields
    0.15
    081
    0.14
    118
    0.14
     toll
    0.14
    perms
    0.13
    sha
    0.13
    eh
    0.13
    oss
    0.13
    Act Density 0.151%

    No Known Activations