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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing potential opportunities or likelihoods of success

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    artner
    -0.18
    usercontent
    -0.16
    Õ¡
    -0.15
    umas
    -0.14
    inge
    -0.14
    ummy
    -0.14
    iya
    -0.13
     pu
    -0.13
    ENE
    -0.13
    .cgi
    -0.13
    POSITIVE LOGITS
     future
    0.20
    future
    0.17
    ikal
    0.16
    isser
    0.15
     Future
    0.15
    _future
    0.15
     chances
    0.14
    æľªæĿ¥
    0.14
     lÃłnh
    0.14
    Future
    0.14
    Act Density 0.327%

    No Known Activations