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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "information" along with related details and instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quirer
    -0.16
    çݲ
    -0.14
     AGAIN
    -0.14
    ctype
    -0.14
    ίθ
    -0.14
    stry
    -0.13
    Ïĥμα
    -0.13
    ¤¤
    -0.13
    ewith
    -0.13
    .pan
    -0.13
    POSITIVE LOGITS
     ab
    0.24
     about
    0.21
     purposes
    0.21
     email
    0.20
     specific
    0.18
     specifics
    0.18
     call
    0.17
    /details
    0.17
     sake
    0.17
     how
    0.16
    Act Density 0.035%

    No Known Activations