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

    Neuronpedia

    INDEX
    Explanations

    names and titles related to historical or cultural figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ModuleName
    -0.15
    .oracle
    -0.15
    tre
    -0.15
    .selector
    -0.15
    amak
    -0.15
    REP
    -0.14
     tre
    -0.14
    ALER
    -0.14
    xac
    -0.14
    arih
    -0.14
    POSITIVE LOGITS
    chen
    0.17
    Gi
    0.15
     Ned
    0.14
     SPDX
    0.14
     XD
    0.14
    egend
    0.14
    ismus
    0.14
     Lud
    0.13
    lei
    0.13
    xford
    0.13
    Act Density 0.091%

    No Known Activations