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

    Neuronpedia

    INDEX
    Explanations

    phrases related to significant political events or actions

    oai_token-act-pair · gpt-3.5-turbo

    significant actions or events related to government decisions and military operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ¥µ
    -0.78
    ãĤ´ãĥ³
    -0.76
    BUT
    -0.74
    ãĥĥãĥī
    -0.73
    ãĥ¤
    -0.71
    +.
    -0.64
    éĹĺ
    -0.62
    $.
    -0.61
    @#&
    -0.60
    ¢
    -0.60
    POSITIVE LOGITS
     ..."
    1.44
     ...
    1.42
     âĢ¦
    1.36
     [...]
    1.24
     âĢ¦"
    1.24
    ..."
    1.23
    ,"
    1.22
    ,''
    1.15
     cannot
    1.13
    âĢ¦"
    1.11
    Act Density 0.464%

    No Known Activations