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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing specific instructions or precautions in a recipe

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -1.98
    ,
    -0.61
     and
    -0.59
    一
    -0.58
    1
    -0.58
    define
    -0.57
    、
    -0.57
    /
    -0.56
    2
    -0.56
    .
    -0.55
    POSITIVE LOGITS
     bandung
    1.56
     Minang
    1.41
     milano
    1.36
     affor
    1.34
     jati
    1.33
     jaya
    1.33
     jawa
    1.33
     Manufact
    1.32
     lele
    1.32
     thut
    1.30
    Act Density 0.890%

    No Known Activations