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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating limitations or constraints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CanadaChoose
    -0.42
    queryInterface
    -0.40
     كومونز
    -0.40
     ProtoMessage
    -0.39
    archie
    -0.39
     pulumi
    -0.39
    classnames
    -0.38
    pely
    -0.37
     FOC
    -0.36
     ARCH
    -0.36
    POSITIVE LOGITS
     aff
    2.66
     Aff
    2.66
     AFF
    2.58
     af
    2.56
    Aff
    2.53
    aff
    2.42
     Af
    2.39
    AFF
    2.31
    Af
    2.27
     AF
    2.06
    Act Density 0.956%

    No Known Activations