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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating progress, advancement, or improvement

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the concept of progress or movement towards a goal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Eg
    -0.70
    Staff
    -0.67
    ashington
    -0.66
    CRIPTION
    -0.65
    UCT
    -0.63
    Synopsis
    -0.63
    Benef
    -0.62
    elligence
    -0.61
    perture
    -0.61
    Card
    -0.59
    POSITIVE LOGITS
     unnoticed
    0.84
    eper
    0.79
    ither
    0.76
     wagon
    0.75
    nova
    0.74
     downhill
    0.74
     overboard
    0.72
     shopping
    0.70
    Ô
    0.70
    wagon
    0.68
    Act Density 0.136%

    No Known Activations