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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the process of condensing or compacting things

    oai_token-act-pair · gpt-3.5-turbo

    words related to sensory perception and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chy
    -0.72
    ngth
    -0.71
    DIR
    -0.70
    bang
    -0.67
    tle
    -0.67
     Lans
    -0.66
    aukee
    -0.64
    kaya
    -0.64
     Rivals
    -0.62
     Werewolf
    -0.61
    POSITIVE LOGITS
    ominium
    1.32
    ensation
    1.26
    ensed
    1.11
    ensing
    1.11
    enser
    1.10
    itional
    1.10
    uctor
    1.05
    itions
    1.04
    uits
    0.99
    uit
    0.92
    Act Density 0.021%

    No Known Activations