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

    Neuronpedia

    INDEX
    Explanations

    actions or situations involving advancement or accumulation

    oai_token-act-pair · gpt-3.5-turbo

    references to actions or items that accumulate or total up

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avers
    -0.78
    Plex
    -0.73
    lect
    -0.67
    ér
    -0.67
    open
    -0.66
    mag
    -0.66
    hent
    -0.66
    clear
    -0.65
    elson
    -0.65
    âĪ
    -0.64
    POSITIVE LOGITS
     conflic
    0.77
     stairs
    0.76
     menus
    0.69
     ante
    0.68
    ikuman
    0.67
     Fight
    0.67
     seams
    0.66
     Ballistic
    0.66
    ĪĴ
    0.64
     defenses
    0.63
    Act Density 0.233%

    No Known Activations