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

    Neuronpedia

    INDEX
    Explanations

    contractions with apostrophes followed by the word 's

    oai_token-act-pair · gpt-3.5-turbo

    phrases that start with "here's."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alties
    -0.79
    soever
    -0.71
    iac
    -0.68
    aneers
    -0.66
    anes
    -0.65
    esm
    -0.65
    nesota
    -0.61
    trust
    -0.61
    doms
    -0.61
    icc
    -0.60
    POSITIVE LOGITS
     hoping
    1.12
     another
    0.82
     why
    0.80
     how
    0.80
     excerpt
    0.80
     whats
    0.76
     what
    0.75
     yours
    0.73
     rundown
    0.72
     kicker
    0.70
    Act Density 0.065%

    No Known Activations