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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating negation or lack of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esson
    -0.15
    halt
    -0.15
    plen
    -0.14
    اØŃ
    -0.14
    idot
    -0.14
    imer
    -0.13
    iry
    -0.13
    perimental
    -0.13
     Esper
    -0.13
    ward
    -0.13
    POSITIVE LOGITS
    sembles
    0.14
    ecal
    0.13
    -global
    0.13
    SWG
    0.13
    .onPause
    0.13
    childs
    0.13
     tük
    0.13
    oje
    0.13
    csi
    0.13
    Ç
    0.13
    Act Density 0.016%

    No Known Activations