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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate reviews or content summaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    כשיו
    -0.48
    AsUp
    -0.47
    יצוב
    -0.46
    ToTable
    -0.45
    icrous
    -0.45
    حياتها
    -0.44
    anskje
    -0.43
    TemporalType
    -0.43
    FormControl
    -0.42
    uchin
    -0.41
    POSITIVE LOGITS
     review
    0.82
     reviewer
    0.79
     reviews
    0.76
     reviewers
    0.72
     reviewing
    0.71
    review
    0.70
     subjective
    0.69
    WithIOException
    0.68
     recens
    0.67
     recensione
    0.66
    Act Density 0.332%

    No Known Activations