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

    Neuronpedia

    INDEX
    Explanations

    keywords related to distribution or distribution-related terms

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "distribution."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    swick
    -0.80
     Cage
    -0.79
     scratch
    -0.77
     Kinnikuman
    -0.71
    glers
    -0.71
    ENA
    -0.68
     masks
    -0.63
     playbook
    -0.61
     framing
    -0.61
     beware
    -0.60
    POSITIVE LOGITS
    ributed
    1.72
    ribut
    1.61
    inguished
    1.61
    ribution
    1.57
    urbed
    1.48
    inct
    1.47
    ribute
    1.46
    raction
    1.44
    rict
    1.42
    ortion
    1.41
    Act Density 0.009%

    No Known Activations