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

    Neuronpedia

    INDEX
    Explanations

    verbs related to physical actions or expressions

    oai_token-act-pair · gpt-3.5-turbo

    actions or activities that denote engagement or involvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dt
    -0.68
    zip
    -0.68
    can
    -0.66
     Kinnikuman
    -0.64
    so
    -0.61
    heim
    -0.59
    lat
    -0.59
    nton
    -0.59
    lo
    -0.59
    net
    -0.58
    POSITIVE LOGITS
    oaded
    0.75
    GGGGGGGG
    0.74
    ADRA
    0.71
     pige
    0.70
    redients
    0.70
    ependent
    0.70
    ipers
    0.68
    ivable
    0.65
    seless
    0.65
    edge
    0.64
    Act Density 0.383%

    No Known Activations