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

    Neuronpedia

    INDEX
    Explanations

    concepts related to security and societal norms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ubu
    -0.17
    æIJ
    -0.16
    ÑĶ
    -0.14
    emiz
    -0.14
    è¾°
    -0.14
    ÑģÑĤеÑĢ
    -0.13
    rena
    -0.13
    @return
    -0.13
    oha
    -0.13
    fly
    -0.13
    POSITIVE LOGITS
    amber
    0.18
     rather
    0.17
     Rather
    0.15
    Rather
    0.15
    rather
    0.15
    antas
    0.14
     fitte
    0.14
    isches
    0.14
    separator
    0.14
    FromArray
    0.13
    Act Density 0.372%

    No Known Activations