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

    Neuronpedia

    INDEX
    Explanations

    terms related to genetic processes or substances

    oai_token-act-pair · gpt-3.5-turbo

    suffixes related to biological or chemical agents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hovah
    -0.75
    avorite
    -0.70
    alion
    -0.68
    eneg
    -0.68
    ategory
    -0.66
    real
    -0.66
    ĵĺ
    -0.65
     hamstring
    -0.65
    erest
    -0.65
    ô
    -0.64
    POSITIVE LOGITS
    etics
    1.29
    etic
    1.22
    etically
    1.16
    ously
    1.10
    ocide
    1.06
    esis
    1.06
    alogy
    0.94
    士
    0.93
    ogen
    0.91
    icity
    0.90
    Act Density 0.017%

    No Known Activations