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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating location or direction

    oai_token-act-pair · gpt-3.5-turbo

    locations or contexts involving concealment or hidden elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sted
    -0.75
    ewitness
    -0.75
     acquainted
    -0.70
    ERROR
    -0.70
    apest
    -0.69
    uku
    -0.69
     aloud
    -0.68
    icer
    -0.66
    uthor
    -0.66
    resh
    -0.66
    POSITIVE LOGITS
     limbo
    0.91
     obscurity
    0.88
     crates
    0.79
     confines
    0.76
     amber
    0.74
     folds
    0.73
     waiting
    0.71
     caches
    0.70
     secrecy
    0.70
     layers
    0.70
    Act Density 0.310%

    No Known Activations