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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and logical connectors in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icky
    -0.16
    orda
    -0.14
    ãĥ©ãĥĥãĤ¯
    -0.14
    CTYPE
    -0.13
    ["$
    -0.13
    Interceptor
    -0.13
    ython
    -0.13
    lena
    -0.13
    ormsg
    -0.13
     and
    -0.13
    POSITIVE LOGITS
    /of
    0.20
    /or
    0.19
    rew
    0.17
    ROID
    0.16
    /OR
    0.15
    REW
    0.15
    icontrol
    0.14
    eh
    0.14
     tarz
    0.14
    omba
    0.14
    Act Density 0.249%

    No Known Activations