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

    Neuronpedia

    INDEX
    Explanations

    symbols and special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,
    -0.53
    -0.51
     (
    -0.49
     and
    -0.48
    ↵
    -0.48
     in
    -0.45
     a
    -0.45
    .
    -0.44
     the
    -0.44
    /
    -0.43
    POSITIVE LOGITS
    ĩ¼
    0.23
    ĺIJ
    0.23
    ĽĪ
    0.23
    ĵ¨
    0.22
    ĥ½
    0.22
    ¹Ħ
    0.22
    -wsj
    0.22
    Įĵ
    0.22
    Ĥ¬
    0.21
    ij¸
    0.21
    Act Density 0.005%

    No Known Activations