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

    Neuronpedia

    INDEX
    Explanations

    mentions of historic firsts or significant achievements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bos
    -0.67
     beaut
    -0.62
     redistributed
    -0.58
     Handling
    -0.57
    leeve
    -0.57
     Refer
    -0.57
    inking
    -0.56
     vis
    -0.55
    ãĥŃ
    -0.54
     aest
    -0.54
    POSITIVE LOGITS
    clusively
    0.89
    eligible
    0.73
    history
    0.70
    opian
    0.70
     history
    0.70
    atts
    0.68
    vironment
    0.67
    owitz
    0.67
    ivably
    0.66
    born
    0.66
    Act Density 0.057%

    No Known Activations