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

    Neuronpedia

    INDEX
    Explanations

    phrases instructing or advising others to remember something specific

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize remembering or keeping in mind certain information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Released
    -0.69
    TPPStreamerBot
    -0.68
    /**
    -0.68
    aku
    -0.68
    way
    -0.66
    Had
    -0.65
    anchester
    -0.64
    folk
    -0.64
     Unloaded
    -0.63
    MpServer
    -0.61
    POSITIVE LOGITS
     beware
    0.99
     caveats
    0.84
    !:
    0.82
     that
    0.82
     however
    0.81
     though
    0.80
     caveat
    0.78
     yourselves
    0.76
     lest
    0.75
     your
    0.75
    Act Density 0.103%

    No Known Activations