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

    Neuronpedia

    INDEX
    Explanations

    terms related to alternative names and descriptions for various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oll
    -0.16
    lic
    -0.15
    usat
    -0.15
    zier
    -0.15
    á»ijt
    -0.14
    OAD
    -0.14
    ouve
    -0.14
    oppel
    -0.14
    κε
    -0.13
    lington
    -0.13
    POSITIVE LOGITS
     known
    0.48
     called
    0.47
     referred
    0.47
    called
    0.38
    known
    0.36
     Known
    0.35
     Called
    0.33
     refer
    0.31
    -known
    0.30
     simply
    0.30
    Act Density 0.064%

    No Known Activations