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

    Neuronpedia

    INDEX
    Explanations

    references to burning or being burned

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fauc
    -0.19
    ibel
    -0.15
    akt
    -0.15
    ials
    -0.15
    531
    -0.15
    oo
    -0.15
    215
    -0.15
    ve
    -0.15
    651
    -0.15
    aden
    -0.14
    POSITIVE LOGITS
     alive
    0.30
    ished
    0.28
     доÑĤ
    0.25
    alive
    0.22
    ISHED
    0.22
    -toast
    0.22
     Alive
    0.22
    ishing
    0.21
     bridges
    0.20
    inated
    0.20
    Act Density 0.032%

    No Known Activations