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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and equations involving variables and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     -
    -0.87
    e
    -0.78
    er
    -0.77
     Table
    -0.76
     Cand
    -0.75
    т
    -0.75
    <i>
    -0.73
    P
    -0.73
     Angela
    -0.71
    PEND
    -0.69
    POSITIVE LOGITS
    -\
    1.19
     raiſ
    1.16
     myſelf
    1.16
     whoſe
    1.15
     Jefus
    1.14
     juſt
    1.12
    =\
    1.11
     pleaſure
    1.10
    .}~\
    1.09
    })+\
    1.09
    Act Density 0.288%

    No Known Activations