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

    Neuronpedia

    INDEX
    Explanations

    the word "simply" and expressions indicating ease or straightforwardness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unj
    -0.16
    utory
    -0.15
    ampler
    -0.15
    ãģĤãģĤ
    -0.15
    ray
    -0.15
    nist
    -0.15
    /gif
    -0.14
    igan
    -0.14
    nid
    -0.14
    sel
    -0.14
    POSITIVE LOGITS
    tons
    0.22
    st
    0.21
    mente
    0.21
     simply
    0.18
    ton
    0.18
    à¹Ĩ
    0.17
    azzo
    0.16
    Simply
    0.16
    TON
    0.16
     Simply
    0.15
    Act Density 0.024%

    No Known Activations