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

    Neuronpedia

    INDEX
    Explanations

    specific phrases or structures in descriptions that emphasize characteristics or features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    305
    -0.18
    yes
    -0.15
    vest
    -0.14
     patron
    -0.13
    arnings
    -0.13
    680
    -0.13
    ÙĪات
    -0.13
    ance
    -0.13
    undler
    -0.13
    绩
    -0.13
    POSITIVE LOGITS
    .CreateInstance
    0.15
    lobe
    0.14
    kol
    0.14
    _MISS
    0.13
    tails
    0.13
    .CheckedChanged
    0.13
    onic
    0.13
    uffix
    0.13
     ty
    0.13
    ffen
    0.13
    Act Density 0.002%

    No Known Activations