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

    Neuronpedia

    INDEX
    Explanations

    words related to work activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ukrain
    -0.76
    olic
    -0.73
    ivas
    -0.64
    itives
    -0.63
    orius
    -0.62
     Bucc
    -0.62
     Axis
    -0.61
    Reviewer
    -0.60
     Neph
    -0.59
    pha
    -0.59
    POSITIVE LOGITS
    aturday
    0.99
    aday
    0.91
    aturdays
    0.91
    holiday
    0.87
    night
    0.86
    lifting
    0.84
    hour
    0.84
     Fridays
    0.83
    day
    0.83
    days
    0.81
    Act Density 0.051%

    No Known Activations