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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and symbols within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    es
    -0.68
     on
    -0.67
     Mar
    -0.64
     C
    -0.62
    </strong>
    -0.57
     in
    -0.55
     Pe
    -0.55
     N
    -0.55
    于
    -0.54
    BeforeClass
    -0.54
    POSITIVE LOGITS
    \[
    1.42
     \[
    1.22
     nakalista
    1.12
     myſelf
    1.05
    \]
    1.04
     ―――――
    1.03
     ſtate
    0.98
     ――――
    0.98
     uſ
    0.98
     \]
    0.96
    Act Density 0.155%

    No Known Activations