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

    Neuronpedia

    INDEX
    Explanations

    comparisons between different types of variables or entities

    oai_token-act-pair · gpt-3.5-turbo

    comparisons between different groups or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pacific
    -0.58
    achine
    -0.58
     revenge
    -0.56
    oval
    -0.56
    FI
    -0.55
     eco
    -0.55
     Nikki
    -0.54
     retro
    -0.54
     immunity
    -0.54
     Carly
    -0.53
    POSITIVE LOGITS
     counterparts
    0.90
    ().
    0.83
     anymore
    0.77
    pees
    0.75
    *.
    0.74
     attRot
    0.73
    +.
    0.72
     existed
    0.71
     nor
    0.71
    $.
    0.70
    Act Density 0.422%

    No Known Activations