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

    Neuronpedia

    INDEX
    Explanations

    news stories or updates

    oai_token-act-pair · gpt-3.5-turbo

    the concept of news stories and reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    viation
    -0.65
    ;;;;;;;;;;;;
    -0.62
    ments
    -0.58
    ersen
    -0.57
    =-=-=-=-
    -0.56
    lessness
    -0.55
     Kessler
    -0.54
    given
    -0.54
    eering
    -0.54
    isoft
    -0.53
    POSITIVE LOGITS
    hots
    0.81
    IDER
    0.77
    matter
    0.67
    ider
    0.66
     sidel
    0.66
     tagged
    0.64
    mith
    0.63
    ospons
    0.61
    hig
    0.60
     trending
    0.60
    Act Density 0.034%

    No Known Activations