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

    Neuronpedia

    INDEX
    Explanations

    phrases related to news organizations or publications

    oai_token-act-pair · gpt-3.5-turbo

    references to specific news organizations or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Turing
    -0.69
    Ô
    -0.64
    igmatic
    -0.63
    assi
    -0.62
     compliment
    -0.61
    amiya
    -0.61
     criminally
    -0.60
     cheating
    -0.59
    ierre
    -0.58
    abbage
    -0.57
    POSITIVE LOGITS
     Newsp
    0.87
    yahoo
    0.82
    office
    0.70
    flash
    0.69
     Malays
    0.68
    umbn
    0.68
    ificant
    0.65
    leases
    0.65
    clinton
    0.64
    Austral
    0.62
    Act Density 0.096%

    No Known Activations