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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to responsibilities and roles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ight
    -0.17
    iner
    -0.16
    ish
    -0.16
     Ramp
    -0.15
    BOR
    -0.15
    ÙĬ
    -0.14
    portion
    -0.13
    punk
    -0.13
    jin
    -0.13
    âu
    -0.13
    POSITIVE LOGITS
    ellipsis
    0.16
    ipse
    0.16
    ntax
    0.15
    SSIP
    0.15
    entin
    0.15
    _mB
    0.15
     sine
    0.15
    ally
    0.15
    ailable
    0.15
    ué
    0.14
    Act Density 0.046%

    No Known Activations