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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to validity and legitimacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ires
    -0.18
    alc
    -0.17
     Rapids
    -0.15
    ef
    -0.15
    aire
    -0.15
    laps
    -0.14
    tps
    -0.14
    CAA
    -0.14
    iel
    -0.14
    eil
    -0.14
    POSITIVE LOGITS
    atable
    0.25
    adera
    0.17
    .Valid
    0.16
    CastException
    0.16
    enticator
    0.15
    ated
    0.15
    .valid
    0.15
    entic
    0.15
    (valid
    0.15
    vet
    0.15
    Act Density 0.043%

    No Known Activations