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

    Neuronpedia

    INDEX
    Explanations

    expressions of certainty and honesty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monument
    -0.14
    ok
    -0.14
     Elm
    -0.14
    ardin
    -0.14
    indh
    -0.14
    éĩ
    -0.14
     resp
    -0.13
    quist
    -0.13
    agon
    -0.13
     Injectable
    -0.13
    POSITIVE LOGITS
    ukkit
    0.16
    rowsing
    0.15
    aired
    0.15
    Charsets
    0.15
    odium
    0.15
    antity
    0.15
    eten
    0.14
    -Sah
    0.14
    OrNil
    0.14
    aeper
    0.14
    Act Density 0.085%

    No Known Activations