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

    Neuronpedia

    INDEX
    Explanations

    references to conclusions and departure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uality
    -0.14
    agn
    -0.14
     çĿ
    -0.13
    sett
    -0.13
     Shapiro
    -0.13
    iks
    -0.13
    ìĦľëĬĶ
    -0.13
    çģ
    -0.12
    050
    -0.12
     unto
    -0.12
    POSITIVE LOGITS
    imde
    0.15
    ordes
    0.15
    uzzer
    0.15
    ricks
    0.14
     (*)(
    0.14
    ìķĻ
    0.14
     Stmt
    0.14
    orde
    0.14
    ’Ñıз
    0.13
     Fucking
    0.13
    Act Density 0.022%

    No Known Activations