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

    Neuronpedia

    INDEX
    Explanations

    phrases related to ongoing events or occurrences

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing ongoing events or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mens
    -0.87
    aments
    -0.83
    ijk
    -0.80
    ament
    -0.77
    stra
    -0.76
    oot
    -0.76
    ilts
    -0.75
    rete
    -0.74
    hetically
    -0.74
    ondo
    -0.73
    POSITIVE LOGITS
     happening
    0.91
     occurring
    0.84
     undone
    0.82
     occurrences
    0.78
     happen
    0.77
     mosqu
    0.76
     events
    0.72
    女
    0.71
    EStream
    0.70
    terday
    0.70
    Act Density 0.009%

    No Known Activations