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

    Neuronpedia

    INDEX
    Explanations

    repeated instances of phrases indicating an increasing trend or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mathematical plus sign

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resultCode
    -0.71
     wireType
    -0.68
    VersionUID
    -0.66
    دانشنامهٔ
    -0.60
     invokingState
    -0.60
    )‏
    -0.58
    MemoryWarning
    -0.58
     ſind
    -0.57
     postIndex
    -0.57
    hWnd
    -0.57
    POSITIVE LOGITS
    +
    1.81
     +
    1.24
    >+</
    1.10
    ()+
    1.09
    }+
    1.08
     $+
    1.07
    &+
    1.06
    +\
    1.05
    $+
    1.05
    +</
    1.03
    Act Density 0.064%

    No Known Activations