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

    Neuronpedia

    INDEX
    Explanations

    terms related to credibility and accreditation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.16
    PERTY
    -0.15
     epic
    -0.15
    ToObject
    -0.14
    opathy
    -0.14
     Sunset
    -0.14
    izador
    -0.14
     Memorial
    -0.14
    aths
    -0.14
    нÑıÑĤ
    -0.14
    POSITIVE LOGITS
    ulous
    0.32
    iting
    0.26
    ibly
    0.25
    ence
    0.25
    ent
    0.24
    ibility
    0.23
    enza
    0.23
    ited
    0.23
    ulously
    0.22
    ible
    0.22
    Act Density 0.004%

    No Known Activations