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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating spatial relationships or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stoff
    -0.17
    rk
    -0.17
    udder
    -0.16
     fleece
    -0.15
    amos
    -0.15
    ssp
    -0.15
    anche
    -0.15
    erie
    -0.15
    jde
    -0.14
    .LookAndFeel
    -0.14
    POSITIVE LOGITS
    ãĤ¦ãĥ³
    0.15
    ihan
    0.15
    roz
    0.14
     Bounty
    0.14
    аÑģÑģ
    0.14
    943
    0.14
    viso
    0.14
     Naw
    0.14
    or
    0.13
     Shaw
    0.13
    Act Density 0.030%

    No Known Activations