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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing associations or connections between different concepts or elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.64
    p
    -0.63
     is
    -0.59
    v
    -0.59
     (
    -0.57
    ↵↵
    -0.54
    on
    -0.52
    P
    -0.52
     -
    -0.51
     –
    -0.51
    POSITIVE LOGITS
     Efq
    1.19
    ]='\
    1.19
    ]--;
    1.16
    ſelves
    1.14
     Majefty
    1.14
     }}$}
    1.13
     leaſt
    1.13
    ſelf
    1.11
     ་་
    1.10
     myſelf
    1.06
    Act Density 0.505%

    No Known Activations