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

    Neuronpedia

    INDEX
    Explanations

    expressions of affection or interest in a positive manner

    oai_token-act-pair · gpt-3.5-turbo

    expressions of desire or affection for something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ongh
    -0.78
    obs
    -0.62
    utical
    -0.61
    ritical
    -0.60
    okes
    -0.59
    VER
    -0.58
    quartered
    -0.58
    arij
    -0.58
    arding
    -0.57
    advant
    -0.57
    POSITIVE LOGITS
     someday
    1.05
    ĺħ
    0.83
     anytime
    0.70
    morrow
    0.66
     Logged
    0.64
     lett
    0.63
    eday
    0.63
    leased
    0.60
     feedback
    0.60
     if
    0.59
    Act Density 0.184%

    No Known Activations