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

    Neuronpedia

    INDEX
    Explanations

    words related to competition and comparison

    oai_token-act-pair · gpt-3.5-turbo

    instances of the prefix "comp-" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lans
    -0.72
     Borough
    -0.65
    vae
    -0.64
     Poles
    -0.64
    thur
    -0.63
     caution
    -0.63
     prevention
    -0.63
     circle
    -0.62
     Grip
    -0.62
    ħĭ
    -0.62
    POSITIVE LOGITS
    ensation
    1.28
    etitive
    1.18
    assion
    1.18
    etition
    1.15
    onents
    1.09
    atibility
    1.09
    ound
    1.07
    rehens
    1.07
    artment
    1.06
    endium
    1.06
    Act Density 0.009%

    No Known Activations