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

    Neuronpedia

    INDEX
    Explanations

    words ending in "se" or "pse" combined with a numerical activation, indicating a specific pattern or code within a text

    oai_token-act-pair · gpt-3.5-turbo

    various forms of the word "seem," indicating an exploration of perception or subjective experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Banner
    -0.77
     overhead
    -0.63
    lessly
    -0.62
     realism
    -0.61
     barr
    -0.60
     BT
    -0.60
     pins
    -0.59
     Lovecraft
    -0.59
     Mellon
    -0.58
     securely
    -0.58
    POSITIVE LOGITS
    gments
    1.43
    venth
    1.42
    ems
    1.35
    ldom
    1.34
    gment
    1.34
    asons
    1.33
    eker
    1.32
    eming
    1.30
    gregation
    1.28
    aled
    1.26
    Act Density 0.029%

    No Known Activations