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

    Neuronpedia

    INDEX
    Explanations

    terms related to proportionality

    oai_token-act-pair · gpt-3.5-turbo

    terms related to proportionality and balance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     residue
    -0.59
    chers
    -0.58
    scl
    -0.57
     reper
    -0.56
     Valhalla
    -0.56
    rosis
    -0.55
     Odin
    -0.52
     livest
    -0.51
     Settlement
    -0.50
     Redemption
    -0.50
    POSITIVE LOGITS
    ately
    2.05
    ate
    2.04
    ally
    1.78
    ality
    1.67
    ates
    1.45
    ated
    1.32
    ationally
    1.31
    amental
    1.31
    aments
    1.24
    ating
    1.22
    Act Density 0.081%

    No Known Activations