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

    Neuronpedia

    INDEX
    Explanations

    phrases and concepts related to moral and ethical themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hick
    -0.16
    ácil
    -0.15
    okit
    -0.15
    zte
    -0.15
    ĴĮ
    -0.15
    arto
    -0.15
    acios
    -0.15
    ochen
    -0.14
     increment
    -0.14
    arte
    -0.14
    POSITIVE LOGITS
    hal
    0.15
    agna
    0.15
    atal
    0.15
    andles
    0.14
    InView
    0.14
    arend
    0.14
    ãĥĥãĤ·ãĥ¥
    0.14
    Encoded
    0.14
    igs
    0.14
     SND
    0.14
    Act Density 0.033%

    No Known Activations