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

    Neuronpedia

    INDEX
    Explanations

    words related to praise or criticism

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific special character or symbol

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reflex
    -0.73
     mounts
    -0.71
     metic
    -0.69
     cloning
    -0.68
     camer
    -0.66
     Patriarch
    -0.66
     apes
    -0.65
     conduc
    -0.65
     vulner
    -0.65
     Tags
    -0.65
    POSITIVE LOGITS
    ever
    1.03
    uthor
    1.02
    null
    0.99
    reci
    0.94
    ternity
    0.94
    cffffcc
    0.92
    lean
    0.89
    ihad
    0.88
    vernment
    0.88
    sure
    0.87
    Act Density 0.177%

    No Known Activations