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

    Neuronpedia

    INDEX
    Explanations

    nested list structures and their corresponding parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ĥ
    -2.91
    ¿½
    -2.70
    ©
    -2.29
    Ĥ¬
    -2.17
    -2.13
    ¸
    -2.13
    ®
    -2.13
    Ĩ
    -2.11
    ı
    -2.06
    Ħ
    -1.96
    POSITIVE LOGITS
     hers
    1.39
    ales
    1.35
    eLife
    1.33
    pos
    1.33
     inbox
    1.31
     possessions
    1.29
    late
    1.28
    quier
    1.27
    responsive
    1.25
    than
    1.24
    Act Density 0.071%

    No Known Activations