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

    Neuronpedia

    INDEX
    Explanations

    names and classifications of species

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _DENIED
    -0.15
    avage
    -0.15
    overe
    -0.15
    æ´²
    -0.14
    _losses
    -0.14
    InstanceState
    -0.14
    _INITIALIZ
    -0.14
     ãĢľ
    -0.14
    義
    -0.13
    vio
    -0.13
    POSITIVE LOGITS
    stead
    0.15
    alian
    0.15
     prob
    0.15
    antic
    0.14
    arians
    0.14
    opia
    0.14
    603
    0.14
    amb
    0.14
     Die
    0.13
    024
    0.13
    Act Density 0.018%

    No Known Activations