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

    Neuronpedia

    INDEX
    Explanations

    names of newspapers and people

    oai_token-act-pair · gpt-3.5-turbo

    references to names or initials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Topic
    -0.71
    é¾įå¥ij士
    -0.70
    âĶĢâĶĢâĶĢâĶĢ
    -0.69
    MK
    -0.67
    uminati
    -0.62
     Forsaken
    -0.60
    ãĤ¤ãĥĪ
    -0.60
    terday
    -0.59
    OPLE
    -0.59
    Unknown
    -0.57
    POSITIVE LOGITS
    ente
    0.77
    ã
    0.69
    isi
    0.69
    ê
    0.69
    uler
    0.67
    oute
    0.66
    uliffe
    0.66
    roma
    0.66
    iasis
    0.66
    onde
    0.65
    Act Density 0.077%

    No Known Activations