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

    Neuronpedia

    INDEX
    Explanations

    words indicative of uncertainty or ambiguity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enek
    -0.16
    ridged
    -0.15
    enor
    -0.15
    readcr
    -0.14
    borg
    -0.14
    รà¸ĩ
    -0.14
    -lfs
    -0.14
    à¹īาà¸ĩ
    -0.14
    _cfg
    -0.14
    ↵
    -0.14
    POSITIVE LOGITS
     towards
    0.18
     oneself
    0.17
     toward
    0.16
     Fowler
    0.16
    kov
    0.15
    ê°ĢìļĶ
    0.15
    onth
    0.15
     Priv
    0.15
    ãĥĩãĥ«
    0.15
    oward
    0.15
    Act Density 0.001%

    No Known Activations