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

    Neuronpedia

    INDEX
    Explanations

    references to academic qualifications or degree titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elage
    -0.16
    907
    -0.16
    amaz
    -0.14
    ehir
    -0.14
    vice
    -0.14
    eff
    -0.13
     Lakes
    -0.13
    ty
    -0.13
    slash
    -0.13
     par
    -0.13
    POSITIVE LOGITS
    uck
    0.16
    ogen
    0.16
    soever
    0.15
    ouse
    0.14
    çIJ´
    0.14
    ucks
    0.14
    ynchronously
    0.14
    TEGER
    0.14
    ologically
    0.14
    idata
    0.14
    Act Density 0.019%

    No Known Activations