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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation or symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eip
    -0.57
     définiti
    -0.57
     Unders
    -0.56
     againſt
    -0.54
     Monfieur
    -0.54
     ſta
    -0.53
     becauſe
    -0.53
    ;">
    -0.52
     podat
    -0.52
     malheureux
    -0.52
    POSITIVE LOGITS
    ConstraintMaker
    0.71
    MENAFN
    0.66
    ddots
    0.60
     autorytatywna
    0.58
    rungsseite
    0.58
    ętr
    0.56
    XtraBars
    0.56
    ⋱
    0.55
    ragalactic
    0.54
    KommentareTeilen
    0.54
    Act Density 0.029%

    No Known Activations