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

    Neuronpedia

    INDEX
    Explanations

    expressions of disappointment, surprise, or shock

    oai_token-act-pair · gpt-3.5-turbo

    expressions of disappointment or sadness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Eucl
    -0.71
     equation
    -0.60
     Edmund
    -0.59
     Origin
    -0.58
     wire
    -0.54
     theorem
    -0.54
     beware
    -0.53
     Drivers
    -0.53
     arsen
    -0.53
     icing
    -0.52
    POSITIVE LOGITS
    !]
    0.80
    ],"
    0.78
    querade
    0.71
    aned
    0.68
    vez
    0.63
    sided
    0.63
    onne
    0.61
    ped
    0.61
    ]);
    0.61
    agos
    0.60
    Act Density 0.214%

    No Known Activations