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

    Neuronpedia

    INDEX
    Explanations

    phrases that introduce additional points or considerations in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     himself
    -0.15
    plr
    -0.14
    amoto
    -0.14
    phin
    -0.14
    rypton
    -0.14
    jumbotron
    -0.14
    ecz
    -0.13
    Ùħد
    -0.13
    maz
    -0.13
    -urlencoded
    -0.13
    POSITIVE LOGITS
     another
    0.16
    anny
    0.15
     Wil
    0.14
     sprink
    0.14
     crusher
    0.14
    Another
    0.14
     thin
    0.14
    REA
    0.14
    izon
    0.14
     merits
    0.14
    Act Density 0.073%

    No Known Activations