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

    Neuronpedia

    INDEX
    Explanations

    locations or events

    oai_token-act-pair · gpt-3.5-turbo

    affirmative statements or declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odge
    -0.72
    eway
    -0.67
    ay
    -0.66
    window
    -0.66
    arel
    -0.66
    space
    -0.66
    oir
    -0.65
    vv
    -0.64
    tube
    -0.64
    earth
    -0.63
    POSITIVE LOGITS
     pedals
    0.83
     MPH
    0.71
     quickest
    0.69
    hift
    0.67
     appropri
    0.66
    ß
    0.65
    Downloadha
    0.64
    ©¶æ
    0.63
    iffe
    0.63
    PDATE
    0.61
    Act Density 0.000%

    No Known Activations