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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating ability and achievement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    èĥ½å¤Ł
    -0.17
     بتÙĪاÙĨ
    -0.17
    ikal
    -0.16
    zu
    -0.15
    dea
    -0.15
    ombo
    -0.15
    à¸ŀà¸Ļ
    -0.14
    zl
    -0.14
     bisa
    -0.14
     Allow
    -0.14
    POSITIVE LOGITS
    -bodied
    0.21
     easily
    0.19
    /disable
    0.17
    ister
    0.17
     afford
    0.16
    berra
    0.16
     freely
    0.16
    ’t
    0.16
    vetica
    0.15
     stomach
    0.15
    Act Density 0.058%

    No Known Activations