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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Whatever" in a text

    oai_token-act-pair · gpt-3.5-turbo

    the word "Whatever" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OWN
    -0.68
    xes
    -0.65
     Papua
    -0.63
     gent
    -0.62
     rabbits
    -0.62
    rael
    -0.60
     ..."
    -0.59
     opposite
    -0.59
    por
    -0.58
     knees
    -0.57
    POSITIVE LOGITS
    theless
    0.87
    lihood
    0.83
    llor
    0.82
    MORE
    0.75
    THING
    0.73
    Correct
    0.73
    leep
    0.70
    body
    0.69
    Whatever
    0.69
    Missing
    0.69
    Act Density 0.022%

    No Known Activations