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

    Neuronpedia

    INDEX
    Explanations

    numerical data or specific measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ContentAlignment
    -0.19
    tics
    -0.16
    tic
    -0.15
    abis
    -0.15
    esses
    -0.15
    ETCH
    -0.14
    otre
    -0.14
    atics
    -0.14
     extra
    -0.14
    _extra
    -0.14
    POSITIVE LOGITS
    d
    0.15
     Chall
    0.14
    ónico
    0.13
    ONTAL
    0.13
    .openg
    0.13
     Ones
    0.13
     panor
    0.13
    شار
    0.13
    him
    0.13
    än
    0.13
    Act Density 0.078%

    No Known Activations