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

    Neuronpedia

    INDEX
    Explanations

    words related to professional and educational qualifications

    oai_token-act-pair · gpt-3.5-turbo

    words related to forms of "to be," including various suffixes and verb endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ²¾
    -0.77
    EStream
    -0.76
    «
    -0.75
     Canaver
    -0.74
    schild
    -0.72
     Newtown
    -0.71
    agall
    -0.68
     shelters
    -0.67
     Palest
    -0.66
     boycot
    -0.65
    POSITIVE LOGITS
    gex
    0.77
    orrect
    0.73
    hander
    0.71
    ously
    0.71
    oop
    0.69
    iation
    0.68
    odo
    0.67
    enough
    0.67
    eness
    0.66
    pec
    0.66
    Act Density 0.251%

    No Known Activations