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

    Neuronpedia

    INDEX
    Explanations

    situations where something is not certain or a decision needs to be made

    oai_token-act-pair · gpt-3.5-turbo

    instances of negation in the context of personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     surv
    -0.45
     pleasures
    -0.44
     pitfalls
    -0.43
     vulner
    -0.43
     miscar
    -0.43
     jog
    -0.43
     pyramid
    -0.42
     pressures
    -0.42
     strat
    -0.42
     misunder
    -0.41
    POSITIVE LOGITS
    ï¸ı
    1.00
    ï¸
    0.66
    âĻ
    0.63
    Balt
    0.63
    tre
    0.63
    _>
    0.59
    £
    0.58
    east
    0.58
    xxx
    0.58
    âĤ¬
    0.58
    Act Density 0.564%

    No Known Activations