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

    Neuronpedia

    INDEX
    Explanations

    mathematical definitions and proofs within a theoretical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arme
    -0.18
    illas
    -0.16
    TTY
    -0.15
    θÎŃ
    -0.15
    uste
    -0.14
     ydk
    -0.14
    Ñıви
    -0.14
     voks
    -0.14
    inent
    -0.14
    TeV
    -0.14
    POSITIVE LOGITS
    \
    0.19
    äºķ
    0.15
     \
    0.15
    ả
    0.14
     Buccane
    0.14
     Burl
    0.14
    aat
    0.14
     Flesh
    0.14
    debit
    0.13
    ARA
    0.13
    Act Density 0.098%

    No Known Activations