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

    Neuronpedia

    INDEX
    Explanations

    phrases related to guidelines and recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ashi
    -0.16
    361
    -0.15
    chw
    -0.15
    cheng
    -0.15
    elif
    -0.15
     cuff
    -0.14
    анÑĤаж
    -0.14
    ache
    -0.14
    273
    -0.14
    atile
    -0.13
    POSITIVE LOGITS
     means
    0.36
    means
    0.31
     meaning
    0.31
     Means
    0.31
    Means
    0.30
    meaning
    0.28
     Meaning
    0.27
     Äijó
    0.24
     mean
    0.24
     bedeut
    0.24
    Act Density 0.131%

    No Known Activations