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

    Neuronpedia

    INDEX
    Explanations

    phrases related to events or information following something else closely

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of "heels."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edia
    -0.75
    abilia
    -0.74
    ourke
    -0.70
    acca
    -0.70
    untu
    -0.69
    entric
    -0.67
    ortion
    -0.66
    tein
    -0.65
    agine
    -0.62
    heddar
    -0.62
    POSITIVE LOGITS
     heels
    1.21
     heel
    0.92
    toe
    0.89
    lash
    0.84
    butt
    0.84
     tail
    0.71
    faced
    0.70
    back
    0.70
     toe
    0.69
     tails
    0.69
    Act Density 0.009%

    No Known Activations