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

    Neuronpedia

    INDEX
    Explanations

    terms related to exaggeration or overemphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sys
    -0.15
    itel
    -0.15
    ikan
    -0.14
    haar
    -0.14
    -basket
    -0.14
    ÑıÑī
    -0.14
    opo
    -0.14
    sWith
    -0.14
    qui
    -0.14
    sm
    -0.14
    POSITIVE LOGITS
    bole
    0.30
    icum
    0.20
    bol
    0.18
    nym
    0.18
     hyper
    0.18
    /Dk
    0.17
    drive
    0.17
    links
    0.17
    activity
    0.15
    loop
    0.15
    Act Density 0.005%

    No Known Activations