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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to measurements or amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -3.05
    ⓧ
    -1.40
    <?
    -1.28
    /**
    -1.22
     intersper
    -1.22
    
    -1.13
     gratify
    -1.03
     amass
    -0.93
     disbur
    -0.92
    /*!
    -0.92
    POSITIVE LOGITS
     seksi
    1.06
     silikon
    0.93
     vasi
    0.92
     optik
    0.91
     kafe
    0.88
     maksi
    0.86
     mikrofon
    0.84
     keramik
    0.83
     corrom
    0.83
     karton
    0.83
    Act Density 0.238%

    No Known Activations