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

    Neuronpedia

    INDEX
    Explanations

    phrases and concepts related to goals and objectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eme
    -0.18
    lij
    -0.15
    eldom
    -0.15
    etim
    -0.15
    ationally
    -0.14
    abbo
    -0.14
    unner
    -0.14
    ppard
    -0.14
    velle
    -0.14
    ehir
    -0.14
    POSITIVE LOGITS
    embros
    0.17
    /target
    0.15
    ramework
    0.15
    óst
    0.15
    .testing
    0.15
    inalg
    0.14
    ären
    0.14
    strike
    0.14
    owing
    0.14
    stead
    0.13
    Act Density 0.021%

    No Known Activations