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

    Neuronpedia

    INDEX
    Explanations

    words related to technology

    oai_token-act-pair · gpt-3.5-turbo

    words associated with teaching or education

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.72
     demographics
    -0.67
     CVE
    -0.65
     containment
    -0.64
     totality
    -0.64
    IFIED
    -0.62
     Hawks
    -0.62
     Icelandic
    -0.61
     Timberwolves
    -0.61
     mistaken
    -0.60
    POSITIVE LOGITS
    legraph
    1.28
    legram
    1.28
    achable
    1.20
    pee
    1.18
    quila
    1.13
    eming
    1.08
    brate
    1.06
    cn
    1.05
    arers
    0.98
    uro
    0.97
    Act Density 0.015%

    No Known Activations