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

    Neuronpedia

    INDEX
    Explanations

    patterns of numerical values and their associations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ỳ
    -0.15
     Wise
    -0.15
    기ëĬĶ
    -0.13
    Ìģ
    -0.13
    Ñĥнк
    -0.13
    jar
    -0.13
    inbox
    -0.13
    krom
    -0.12
    ENN
    -0.12
    Ä©
    -0.12
    POSITIVE LOGITS
    0
    0.51
    âĤĢ
    0.28
     zero
    0.28
    Û°
    0.28
    ï¼IJ
    0.27
    ०
    0.26
    00
    0.26
    Ùł
    0.23
    -zero
    0.21
    鼶
    0.21
    Act Density 0.178%

    No Known Activations