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

    Neuronpedia

    INDEX
    Explanations

    discussions around experience and the interplay between knowledge and competence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     REALLY
    -0.20
     VERY
    -0.17
     WOW
    -0.15
     HUGE
    -0.14
     (@
    -0.14
    ;↵↵
    -0.14
    unos
    -0.14
    ;↵
    -0.14
     ??
    -0.14
     BIG
    -0.13
    POSITIVE LOGITS
     _
    0.77
     **
    0.38
    -_
    0.37
     *
    0.34
     !_
    0.31
     *_
    0.30
     ._
    0.27
     _|
    0.26
     {\
    0.24
     __
    0.24
    Act Density 0.927%

    No Known Activations