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

    Neuronpedia

    INDEX
    Explanations

    words related to pre-existing conditions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'x' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pru
    -0.82
     Courage
    -0.73
     Rough
    -0.70
     Kirin
    -0.65
    £ı
    -0.62
    kson
    -0.62
     behavi
    -0.61
    ¢
    -0.60
    GROUND
    -0.60
     streng
    -0.60
    POSITIVE LOGITS
    aminer
    1.17
    avier
    1.13
    posure
    1.10
    ample
    1.09
    imity
    1.07
    actly
    1.07
    cellence
    1.07
    press
    1.06
    odus
    1.05
    cellent
    1.04
    Act Density 0.036%

    No Known Activations