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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific places or destinations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a type of destination or purpose

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    notations
    -0.78
    htar
    -0.68
     cords
    -0.67
    dad
    -0.64
     Transcript
    -0.63
    urances
    -0.61
     warranties
    -0.61
     curves
    -0.61
    ptive
    -0.60
    Å¡
    -0.60
    POSITIVE LOGITS
     sorts
    0.78
     beginners
    0.77
    inel
    0.71
    geries
    0.71
     disguise
    0.69
     behold
    0.69
     everyday
    0.67
     beginner
    0.66
     many
    0.66
     distraction
    0.66
    Act Density 0.264%

    No Known Activations