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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs indicating a continuing state or action

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the word "still."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    insula
    -0.83
    thood
    -0.76
    stice
    -0.76
    onential
    -0.74
    ridges
    -0.73
    velt
    -0.69
    alties
    -0.67
     SQ
    -0.66
     Stim
    -0.66
    ãĥ³ãĤ¸
    -0.66
    POSITIVE LOGITS
     intact
    0.87
     undecided
    0.84
    birth
    0.82
    born
    0.81
     recovering
    0.81
     reeling
    0.80
     alive
    0.79
     technically
    0.78
     undergoing
    0.75
     viable
    0.75
    Act Density 0.040%

    No Known Activations