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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a sense of complexity or contradiction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ellig
    -0.15
    JKLMNOP
    -0.15
    avl
    -0.14
    ADX
    -0.14
    .dense
    -0.14
    argin
    -0.14
    ovsky
    -0.14
    .lst
    -0.14
    ermann
    -0.14
    inalg
    -0.13
    POSITIVE LOGITS
     Sala
    0.16
     nature
    0.15
     enough
    0.14
     Nature
    0.14
    ness
    0.14
     SAC
    0.14
     stalk
    0.14
    wend
    0.14
     sac
    0.13
    stalk
    0.13
    Act Density 0.284%

    No Known Activations