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

    Neuronpedia

    INDEX
    Explanations

    the names of places

    oai_token-act-pair · gpt-3.5-turbo

    elements related to dramatic or noteworthy events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Cause
    -0.73
    ossibility
    -0.72
     cannot
    -0.72
     contam
    -0.69
     dunno
    -0.67
     sue
    -0.66
    erity
    -0.65
     violates
    -0.65
    hovah
    -0.64
    },{"
    -0.64
    POSITIVE LOGITS
     Saturday
    0.93
     Thursday
    0.91
     Wednesday
    0.89
     Friday
    0.87
     Tuesday
    0.84
     Sunday
    0.84
     Saturdays
    0.82
     outings
    0.81
     Monday
    0.81
     evenings
    0.81
    Act Density 0.809%

    No Known Activations