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

    Neuronpedia

    INDEX
    Explanations

    terms and conditions related to mathematical proofs and assumptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akis
    -0.15
    oleÄį
    -0.15
    bootstrap
    -0.15
    utta
    -0.14
    verte
    -0.14
    kest
    -0.14
    ics
    -0.14
    ira
    -0.14
    776
    -0.14
    olla
    -0.14
    POSITIVE LOGITS
    oland
    0.16
    òi
    0.16
    _THAT
    0.15
    iel
    0.14
     rip
    0.14
    rieving
    0.14
    .DataType
    0.14
     vol
    0.13
    rief
    0.13
     TMPro
    0.13
    Act Density 0.065%

    No Known Activations