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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating emotional responses or reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elden
    -0.16
    EDIUM
    -0.15
     Bradley
    -0.15
    ãĤ²
    -0.15
    arme
    -0.15
    ÌĨ
    -0.14
    aptive
    -0.14
    mtree
    -0.14
    Slf
    -0.14
    hv
    -0.14
    POSITIVE LOGITS
    ik
    0.14
    epad
    0.13
    kek
    0.13
    rar
    0.13
    izm
    0.13
    qa
    0.13
    ccb
    0.13
    ames
    0.13
    itia
    0.13
     somehow
    0.13
    Act Density 0.213%

    No Known Activations