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

    Neuronpedia

    INDEX
    Explanations

    words related to computer hardware processing units and specifications

    oai_token-act-pair · gpt-3.5-turbo

    terms related to resources or materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     messenger
    -0.66
     Airl
    -0.63
    jab
    -0.63
     Hemp
    -0.62
    SpaceEngineers
    -0.62
     plane
    -0.60
     disclaimer
    -0.60
     responders
    -0.60
    talk
    -0.60
    ulk
    -0.59
    POSITIVE LOGITS
    ources
    0.91
    ores
    0.90
    pace
    0.90
    hift
    0.82
    pring
    0.82
    ource
    0.81
    ystem
    0.80
    tto
    0.80
    gon
    0.79
    kin
    0.79
    Act Density 0.010%

    No Known Activations