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

    Neuronpedia

    INDEX
    Explanations

    words related to news articles and reports

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    OWS
    -0.69
    UTION
    -0.67
    ometers
    -0.67
    é¾įå
    -0.66
    NPR
    -0.65
    ometer
    -0.63
    EMBER
    -0.62
    igate
    -0.60
    STEP
    -0.60
    RL
    -0.59
    POSITIVE LOGITS
    Magikarp
    1.37
    sin
    0.86
    uits
    0.84
    sa
    0.83
    hire
    0.80
    ystem
    0.79
    sein
    0.79
    er
    0.78
    hip
    0.76
    gue
    0.76
    Act Density 0.039%

    No Known Activations