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

    Neuronpedia

    INDEX
    Explanations

    references to notable achievements and awards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ftar
    -0.19
    ahat
    -0.16
    ãĥķãĥ¬
    -0.16
    aines
    -0.16
    ingroup
    -0.15
    PHA
    -0.15
     ah
    -0.15
    SHA
    -0.14
    amac
    -0.14
    rou
    -0.14
    POSITIVE LOGITS
    íĤ¹
    0.16
     Giles
    0.15
     Teddy
    0.14
     Ritch
    0.14
     Erotische
    0.14
    inja
    0.14
    agli
    0.14
    [js
    0.14
     Rig
    0.13
     Elliot
    0.13
    Act Density 0.034%

    No Known Activations