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

    Neuronpedia

    INDEX
    Explanations

    summaries and descriptions of various subjects or themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enci
    -0.16
    ataires
    -0.16
    ynes
    -0.14
    iset
    -0.14
    pez
    -0.14
    ijk
    -0.14
    _compat
    -0.14
    еÑĢо
    -0.13
    umhur
    -0.13
    343
    -0.13
    POSITIVE LOGITS
     how
    0.26
     sorts
    0.24
     what
    0.20
    how
    0.17
     current
    0.16
     Ñģобой
    0.15
     activity
    0.15
     why
    0.15
     exactly
    0.15
    ora
    0.14
    Act Density 0.119%

    No Known Activations