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

    Neuronpedia

    INDEX
    Explanations

    terminology related to agreements or stipulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     تÙĦ
    -0.15
     Dud
    -0.14
    uell
    -0.14
    _ATTRIBUTES
    -0.13
    eyen
    -0.13
     Proceed
    -0.13
    -coded
    -0.13
     chill
    -0.13
    ader
    -0.13
     Chop
    -0.13
    POSITIVE LOGITS
    ocol
    0.18
    ylon
    0.18
    gy
    0.17
    éĤ¦
    0.17
    stice
    0.16
    racak
    0.15
    ioc
    0.15
    dio
    0.15
    bose
    0.15
    lope
    0.15
    Act Density 0.005%

    No Known Activations