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

    Neuronpedia

    INDEX
    Explanations

    phrases related to media outlets

    oai_token-act-pair · gpt-3.5-turbo

    references to various media outlets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heed
    -0.82
     Defin
    -0.70
    ohan
    -0.69
    eric
    -0.69
    ipeg
    -0.65
    birds
    -0.64
    tnc
    -0.63
    ãĥĥãĥī
    -0.61
     Feather
    -0.61
    heart
    -0.60
    POSITIVE LOGITS
     outlets
    1.03
     outlet
    1.02
    eval
    0.73
    swick
    0.72
     ende
    0.72
    ror
    0.67
     Wem
    0.65
    ="#
    0.65
    prises
    0.65
    prise
    0.64
    Act Density 0.036%

    No Known Activations