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

    Neuronpedia

    INDEX
    Explanations

    phrases or expressions indicating a reduction or lower amount

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oug
    -0.16
    tas
    -0.15
    trl
    -0.14
    ulist
    -0.14
    pas
    -0.14
    ady
    -0.14
    issy
    -0.14
    erken
    -0.14
     Resp
    -0.14
    Å«
    -0.13
    POSITIVE LOGITS
    ened
    0.44
    ening
    0.43
    -than
    0.39
     than
    0.36
    Than
    0.31
    _than
    0.30
    ens
    0.27
     Than
    0.27
     THAN
    0.27
    ons
    0.27
    Act Density 0.032%

    No Known Activations