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

    Neuronpedia

    INDEX
    Explanations

    short phrases related to storytelling or personal reflections

    oai_token-act-pair · gpt-3.5-turbo

    general statements or remarks made by various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.72
    arching
    -0.71
     arisen
    -0.71
     conver
    -0.69
    ¥ŀ
    -0.68
     '.
    -0.67
    conservancy
    -0.66
     substrate
    -0.65
    artifacts
    -0.65
    frequency
    -0.63
    POSITIVE LOGITS
    Said
    0.93
     quotes
    0.89
    upon
    0.72
     Said
    0.71
    Words
    0.70
     quoted
    0.70
     Oaks
    0.70
     quotation
    0.66
    ["
    0.65
     "...
    0.65
    Act Density 0.536%

    No Known Activations