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

    Neuronpedia

    INDEX
    Explanations

    technical alphanumeric patterns and strings, possibly related to computer programming or identification codes

    oai_token-act-pair · gpt-3.5-turbo

    character sequences or codes commonly associated with technical or software identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     closures
    -0.72
     scrut
    -0.69
     closure
    -0.67
     princ
    -0.64
     lamb
    -0.64
     barred
    -0.63
     prohibition
    -0.63
     compan
    -0.63
     spectator
    -0.62
     breat
    -0.61
    POSITIVE LOGITS
    dq
    1.03
    _-
    0.96
    AAAA
    0.94
    IU
    0.92
    rl
    0.90
    AAA
    0.88
    Lv
    0.87
    001
    0.85
    dn
    0.85
    OY
    0.85
    Act Density 0.131%

    No Known Activations