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

    Neuronpedia

    INDEX
    Explanations

    adjectives that emphasize magnitude or intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iac
    -0.15
    _hz
    -0.14
    iam
    -0.14
    ãģ¡ãĤĥ
    -0.13
    oz
    -0.13
    avi
    -0.13
    orr
    -0.13
     Mayer
    -0.13
    seau
    -0.13
    ädchen
    -0.13
    POSITIVE LOGITS
    ê¸ī
    0.15
    Ø´ÙĪ
    0.14
    vrier
    0.14
    lien
    0.14
    IBUTE
    0.14
     cons
    0.14
    ئت
    0.14
    oshi
    0.13
    gi
    0.13
    IFA
    0.13
    Act Density 0.001%

    No Known Activations