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

    Neuronpedia

    INDEX
    Explanations

    comparisons and evaluations using the word "like"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express comparisons or opinions about situations or things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ascript
    -0.89
     ashore
    -0.82
    enhagen
    -0.78
    auga
    -0.76
    代
    -0.73
    enberg
    -0.71
    milo
    -0.71
    herer
    -0.70
    onductor
    -0.70
    agos
    -0.69
    POSITIVE LOGITS
     quaint
    0.85
     contradiction
    0.83
     innocuous
    0.78
    pmwiki
    0.77
     oxy
    0.77
     plausible
    0.76
     logical
    0.75
     coincidence
    0.74
     deviation
    0.71
     cliché
    0.70
    Act Density 0.114%

    No Known Activations