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

    Neuronpedia

    INDEX
    Explanations

    references to literary works and authors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    èĨľ
    -0.16
    EO
    -0.15
    ROME
    -0.15
    ".$_
    -0.15
    anoia
    -0.14
    traffic
    -0.14
    istros
    -0.14
    GH
    -0.14
    949
    -0.14
    494
    -0.14
    POSITIVE LOGITS
     Huck
    0.35
     Tw
    0.30
     Mark
    0.24
     Clem
    0.24
     Finn
    0.23
     Mississippi
    0.22
     Missouri
    0.21
    Tw
    0.21
     raft
    0.20
     Hann
    0.20
    Act Density 0.009%

    No Known Activations