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

    Neuronpedia

    INDEX
    Explanations

    invalid or corrupted email addresses

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases or structures within a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ichick
    -0.73
    swer
    -0.70
    halla
    -0.67
    qs
    -0.67
     Squadron
    -0.64
    llular
    -0.64
     purs
    -0.64
    urat
    -0.63
     baseline
    -0.61
    ilaterally
    -0.60
    POSITIVE LOGITS
    Actor
    0.81
    PORT
    0.72
    Britain
    0.71
    BBC
    0.70
    Sorry
    0.68
    THIS
    0.67
    Scotland
    0.65
    Warning
    0.65
    ãĤ¨ãĥ«
    0.64
    TOR
    0.63
    Act Density 0.041%

    No Known Activations