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

    Neuronpedia

    INDEX
    Explanations

    words related to names and references to individuals or groups in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Galileo
    -0.72
     Croat
    -0.71
    achev
    -0.71
     Galile
    -0.70
     Croatian
    -0.68
     Ragnarok
    -0.64
     Premiere
    -0.60
     srfAttach
    -0.59
     Prophet
    -0.59
     nutshell
    -0.59
    POSITIVE LOGITS
    ney
    0.85
    lish
    0.83
    cheon
    0.82
    urdy
    0.77
    rey
    0.77
    lear
    0.76
    KY
    0.76
    zynski
    0.76
    lee
    0.75
    houn
    0.73
    Act Density 0.014%

    No Known Activations