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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "flare" or related words

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "flare" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ele
    -0.85
    nesota
    -0.82
    rified
    -0.82
    ittee
    -0.77
    ointed
    -0.74
    esson
    -0.74
    OTE
    -0.73
    ipeg
    -0.72
    phis
    -0.72
    egg
    -0.71
    POSITIVE LOGITS
     flares
    1.50
     flare
    1.26
     flared
    1.08
     lamps
    0.78
     eru
    0.77
     spraying
    0.75
     brighter
    0.74
    crow
    0.74
    lights
    0.73
     capacitor
    0.73
    Act Density 0.009%

    No Known Activations