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

    Neuronpedia

    INDEX
    Explanations

    queries asking for opinions or thoughts

    oai_token-act-pair · gpt-3.5-turbo

    phrases asking for opinions or thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ylum
    -0.75
    âĢ¢âĢ¢
    -0.70
    enges
    -0.69
    geries
    -0.68
    adr
    -0.65
    Lago
    -0.64
    ocol
    -0.63
    doors
    -0.61
    ait
    -0.60
    fig
    -0.60
    POSITIVE LOGITS
     guys
    1.06
     prefer
    0.87
     think
    0.85
     favourite
    0.82
     propose
    0.78
     recommend
    0.77
     choose
    0.75
     anticipate
    0.75
    ?'
    0.75
     favorite
    0.74
    Act Density 0.041%

    No Known Activations