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

    Neuronpedia

    INDEX
    Explanations

    alphanumeric codes or identifiers ending in 'EN' followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    information related to energy or environmental topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ronaldo
    -0.71
     Monica
    -0.66
    mson
    -0.65
     hitch
    -0.61
    plane
    -0.60
     Manz
    -0.58
    tor
    -0.58
    zzi
    -0.58
    axe
    -0.58
     Fernand
    -0.57
    POSITIVE LOGITS
    TERN
    1.08
    ISH
    1.02
    ET
    1.01
    ECA
    0.99
    AME
    0.97
    ERAL
    0.97
    HCR
    0.97
    vironment
    0.96
    ABLE
    0.96
    emies
    0.96
    Act Density 0.008%

    No Known Activations