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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing the level of difficulty

    oai_token-act-pair · gpt-3.5-turbo

    adjectives related to the difficulty or ease of tasks and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erity
    -0.64
     Noon
    -0.63
    inas
    -0.58
    Austral
    -0.56
    çīĪ
    -0.56
    gemony
    -0.56
    usha
    -0.55
    ACY
    -0.55
     Brief
    -0.55
     Anthem
    -0.54
    POSITIVE LOGITS
     to
    0.94
    coded
    0.79
    going
    0.78
    to
    0.72
    wired
    0.71
     terrain
    0.71
    bodied
    0.69
     unto
    0.66
    ranged
    0.64
    ãĥ©
    0.63
    Act Density 0.094%

    No Known Activations