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

    Neuronpedia

    INDEX
    Explanations

    phrases that discuss various problems or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    linger
    -0.19
    دث
    -0.15
    ure
    -0.15
    /rules
    -0.15
    urch
    -0.15
     Equals
    -0.15
    wij
    -0.14
    owler
    -0.14
    imler
    -0.14
    /wiki
    -0.14
    POSITIVE LOGITS
    ahl
    0.15
    akah
    0.15
    ladu
    0.15
     lack
    0.15
     Stap
    0.14
    chief
    0.14
    -Ñħ
    0.14
    ëĥ¥
    0.14
    dbus
    0.13
    ometr
    0.13
    Act Density 0.141%

    No Known Activations