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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "all"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ALL" and similar variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hered
    -0.87
    elsen
    -0.76
    yip
    -0.74
    paio
    -0.71
     unfocusedRange
    -0.70
    aldi
    -0.68
    Balt
    -0.68
    nai
    -0.67
    EStream
    -0.66
    erey
    -0.65
    POSITIVE LOGITS
    OWS
    0.96
    IED
    0.95
    ocations
    0.91
    adium
    0.87
    OW
    0.85
    BACK
    0.85
    ength
    0.82
    ocated
    0.82
    OC
    0.81
    ORY
    0.81
    Act Density 0.012%

    No Known Activations