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

    Neuronpedia

    INDEX
    Explanations

    specific phrases related to determinations or verdicts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to loss and its emotional impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     a
    -0.54
     an
    -0.50
     virginity
    -0.49
     MIDI
    -0.48
     Vintage
    -0.48
     vintage
    -0.46
     Literature
    -0.46
     typew
    -0.45
     Papers
    -0.45
     metric
    -0.45
    POSITIVE LOGITS
    each
    0.74
    none
    0.70
    ichever
    0.69
    together
    0.69
    andem
    0.66
    both
    0.64
    Together
    0.64
    ////////////////
    0.63
    rick
    0.62
    other
    0.61
    Act Density 0.926%

    No Known Activations