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

    Neuronpedia

    INDEX
    Explanations

    words and phrases associated with descriptions of violent events and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     "/";↵
    -0.15
     @"";↵
    -0.14
    =@
    -0.13
     à¤Ĩà¤ĸ
    -0.13
     ../../../
    -0.13
     '/';↵
    -0.13
     @"\
    -0.13
    ä½ķãģĭ
    -0.12
    sterol
    -0.12
    SCI
    -0.12
    POSITIVE LOGITS
     "
    0.43
     '
    0.38
     «
    0.31
     “
    0.30
     \"
    0.29
     `
    0.28
     ``
    0.27
    ãĢĮ
    0.27
     ‘
    0.26
     ''
    0.24
    Act Density 0.225%

    No Known Activations