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

    Neuronpedia

    INDEX
    Explanations

    repeated phrases and themes related to patterns of communication or connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Esc
    -0.16
    arness
    -0.16
    arg
    -0.16
    sterol
    -0.15
     Esc
    -0.14
    ospace
    -0.14
     ster
    -0.14
    ledon
    -0.14
    ildenafil
    -0.14
    rosse
    -0.14
    POSITIVE LOGITS
     RTS
    0.15
     flash
    0.15
    Flash
    0.15
     Flash
    0.14
    å¾ĭ
    0.14
     Už
    0.14
    orum
    0.14
    138
    0.14
     Ges
    0.14
    _hooks
    0.14
    Act Density 0.004%

    No Known Activations