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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a statement of what should occur or what is expected

    oai_token-act-pair · gpt-3.5-turbo

    statements expressing necessity or recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     maze
    -0.73
     opium
    -0.69
    hole
    -0.68
    ories
    -0.68
     Wid
    -0.67
     hostage
    -0.65
     Magnetic
    -0.64
     coma
    -0.64
     Puzzle
    -0.64
     Trails
    -0.64
    POSITIVE LOGITS
    arna
    0.90
    ghai
    0.74
     judged
    0.74
    eele
    0.74
    amation
    0.73
    autions
    0.71
    rifice
    0.69
    arers
    0.68
    erto
    0.68
    cellence
    0.68
    Act Density 0.183%

    No Known Activations