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

    Neuronpedia

    INDEX
    Explanations

    phrases related to professions serving a specific group or community

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to relationships and community interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pere
    -0.63
     coincidence
    -0.61
     convergence
    -0.60
     frontal
    -0.60
     Pun
    -0.59
     psychiatrists
    -0.58
     Priest
    -0.57
     spoiler
    -0.57
     Kle
    -0.57
     Ballard
    -0.56
    POSITIVE LOGITS
     dearly
    0.84
    */(
    0.71
    paio
    0.70
    .'
    0.67
    é¾įåĸļ士
    0.67
    ient
    0.66
    )].
    0.66
    .'"
    0.66
    amines
    0.64
    ugen
    0.63
    Act Density 0.197%

    No Known Activations