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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditional or hypothetical situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    egis
    -0.19
    ynam
    -0.15
    urat
    -0.15
    sson
    -0.14
    nock
    -0.14
     Tradable
    -0.14
    cken
    -0.14
    ahren
    -0.14
    igua
    -0.14
    aldi
    -0.14
    POSITIVE LOGITS
    .compiler
    0.15
    soever
    0.15
    ever
    0.14
    ÅŁa
    0.14
     Devils
    0.14
    addon
    0.14
    redicate
    0.13
    Ŀi
    0.13
    Installer
    0.13
    ared
    0.13
    Act Density 0.051%

    No Known Activations