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

    Neuronpedia

    INDEX
    Explanations

    collocations of the word "and" along with structure or conjunctions in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Brom
    -0.17
     Inquiry
    -0.15
    ower
    -0.15
    doll
    -0.14
     Mess
    -0.14
    Ñĥж
    -0.13
     scramble
    -0.13
    ãĤ¦ãĥ³
    -0.13
    æ®ĸ
    -0.13
    edian
    -0.13
    POSITIVE LOGITS
    åIJ§
    0.19
    isia
    0.16
    561
    0.16
     kurtul
    0.15
    769
    0.15
     yourselves
    0.15
    å°½
    0.15
     yourself
    0.15
    dont
    0.14
     Proceed
    0.14
    Act Density 0.095%

    No Known Activations