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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "only to"

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a sequence of actions or events leading to an outcome

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onics
    -0.79
    anti
    -0.69
    mob
    -0.66
    orean
    -0.65
    oug
    -0.64
    ore
    -0.64
    aim
    -0.64
    ove
    -0.62
     Mercury
    -0.61
    medium
    -0.60
    POSITIVE LOGITS
     refill
    0.77
     realize
    0.74
     beg
    0.72
     realise
    0.72
     remind
    0.71
    strom
    0.71
     succumb
    0.69
     reapp
    0.69
    iffe
    0.68
     subsequently
    0.68
    Act Density 0.047%

    No Known Activations