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

    Neuronpedia

    INDEX
    Explanations

    references to procedural changes and updates in a formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    loff
    -0.16
    ahlen
    -0.15
    lle
    -0.15
    /lo
    -0.15
    ilde
    -0.14
     Milk
    -0.14
    athan
    -0.14
    çĩ
    -0.14
    ighb
    -0.14
     kalk
    -0.14
    POSITIVE LOGITS
     court
    0.31
    -court
    0.29
     courts
    0.28
     cour
    0.28
    court
    0.27
    cour
    0.26
    Cour
    0.26
     civil
    0.26
     pilots
    0.25
    Court
    0.24
    Act Density 0.005%

    No Known Activations