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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "information" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uko
    -0.20
    Info
    -0.16
    pty
    -0.15
    info
    -0.15
    (es
    -0.15
    pressive
    -0.15
    ler
    -0.14
    dogs
    -0.14
    _info
    -0.14
    خاÙĨÙĩ
    -0.14
    POSITIVE LOGITS
     about
    0.33
    _about
    0.25
    ally
    0.24
    about
    0.23
    -sharing
    0.22
     sources
    0.22
    /data
    0.21
     sheets
    0.21
     About
    0.21
     tentang
    0.21
    Act Density 0.090%

    No Known Activations