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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "for"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emachine
    -0.18
    _hi
    -0.15
    ãĥ¼ãĥ«ãĥī
    -0.15
    reu
    -0.15
    uhe
    -0.15
     massa
    -0.14
     Hi
    -0.14
     hi
    -0.14
    kla
    -0.14
    hesion
    -0.14
    POSITIVE LOGITS
    Ñĭл
    0.17
    @show
    0.16
    OOK
    0.16
    iens
    0.15
     Licht
    0.15
    iba
    0.14
    ensa
    0.14
    abi
    0.14
    unity
    0.13
    bab
    0.13
    Act Density 0.080%

    No Known Activations