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

    Neuronpedia

    INDEX
    Explanations

    names and references to historical figures and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aeda
    -0.17
    idunt
    -0.16
    urum
    -0.15
    reh
    -0.15
    gorit
    -0.15
    bakan
    -0.15
    aket
    -0.14
    uellement
    -0.14
     currently
    -0.14
     mastur
    -0.14
    POSITIVE LOGITS
     pole
    0.18
    152
    0.16
     propag
    0.16
     propaganda
    0.15
    Mgr
    0.15
     contacts
    0.15
     favor
    0.15
     pap
    0.15
    -CS
    0.14
    ophile
    0.14
    Act Density 0.037%

    No Known Activations