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

    Neuronpedia

    INDEX
    Explanations

    positive evaluations or feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     coated
    -0.15
     Sovere
    -0.14
    swick
    -0.14
    clair
    -0.14
    hed
    -0.14
    rial
    -0.14
    ManagedObject
    -0.14
    ustum
    -0.14
    ForKey
    -0.13
    HONE
    -0.13
    POSITIVE LOGITS
     Kak
    0.15
    owler
    0.15
    ilha
    0.15
     activeClassName
    0.14
    abor
    0.14
    itom
    0.14
     Knock
    0.14
     yolu
    0.14
    iel
    0.13
    enburg
    0.13
    Act Density 0.065%

    No Known Activations