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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating progression or directionality towards a goal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    entina
    -0.17
     continued
    -0.16
    ãĥ¼ãĥ«
    -0.15
    emain
    -0.15
    foil
    -0.14
    uries
    -0.14
     Weiter
    -0.14
    continued
    -0.14
    lut
    -0.14
    entifier
    -0.14
    POSITIVE LOGITS
    nings
    0.17
    INGS
    0.15
    ings
    0.14
    ycz
    0.14
    icode
    0.14
    (er
    0.14
    QUEST
    0.14
    inde
    0.13
     conc
    0.13
    XHR
    0.13
    Act Density 0.015%

    No Known Activations