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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating progress or advancement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iko
    -0.15
    ieres
    -0.14
     witness
    -0.13
     Gör
    -0.13
    688
    -0.13
    hab
    -0.13
    mul
    -0.13
    JD
    -0.13
     cables
    -0.13
    iculo
    -0.13
    POSITIVE LOGITS
     libertin
    0.15
     MatSnackBar
    0.15
    agt
    0.14
    éĤ¦
    0.14
    ears
    0.14
    æ¨Ļ
    0.14
    oppable
    0.14
     Collective
    0.14
    OrElse
    0.14
    anco
    0.13
    Act Density 0.015%

    No Known Activations