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

    Neuronpedia

    INDEX
    Explanations

    references to biases and misconceptions in perception and evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shouldBe
    -0.15
    erif
    -0.15
    andal
    -0.14
    oriously
    -0.13
    (always
    -0.13
    ifdef
    -0.13
    enkins
    -0.13
    _typeof
    -0.12
     youre
    -0.12
    etat
    -0.12
    POSITIVE LOGITS
     doesn
    0.71
     nicht
    0.60
     didn
    0.60
     tidak
    0.60
     isn
    0.59
     não
    0.56
     neither
    0.56
     wasn
    0.56
     does
    0.55
     niet
    0.53
    Act Density 1.812%

    No Known Activations