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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to political figures and significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    perse
    -0.45
    NetMessage
    -0.44
    OPA
    -0.43
    laus
    -0.43
    venge
    -0.40
    rg
    -0.40
     Recon
    -0.39
    semble
    -0.39
    ramid
    -0.38
    haar
    -0.38
    POSITIVE LOGITS
    halla
    0.51
    querque
    0.46
    isphere
    0.42
     equivalents
    0.42
     detract
    0.41
     outweigh
    0.41
     lasts
    0.40
    igible
    0.40
    oided
    0.40
     rivals
    0.40
    Act Density 2.958%

    No Known Activations