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

    Neuronpedia

    INDEX
    Explanations

    specific codes or identifiers, possibly related to coding syntax or mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mavericks
    -0.79
     venture
    -0.67
     patched
    -0.67
     charm
    -0.65
     Soft
    -0.64
     sanctions
    -0.64
     gossip
    -0.63
     cocktail
    -0.63
     conflic
    -0.62
     Typhoon
    -0.61
    POSITIVE LOGITS
    ħ
    1.19
    Ļ
    1.18
    Ì
    1.16
    ³
    1.14
    ©
    1.12
    ¹
    1.09
    ¯
    1.09
    ¸
    1.08
    ª
    1.06
    Ħ
    1.04
    Act Density 0.899%

    No Known Activations