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

    Neuronpedia

    INDEX
    Explanations

    affirmative phrases or expressions of certainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ificio
    -0.15
    gf
    -0.14
    SOC
    -0.14
    acman
    -0.14
    elsey
    -0.14
     ÑĤаким
    -0.14
    UFF
    -0.14
    stad
    -0.13
    ssi
    -0.13
    IGHLIGHT
    -0.13
    POSITIVE LOGITS
    um
    0.15
    .setUp
    0.14
    arding
    0.13
    /pro
    0.13
    aux
    0.13
    lue
    0.13
    alg
    0.12
    un
    0.12
     Ki
    0.12
    tas
    0.12
    Act Density 0.033%

    No Known Activations