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

    Neuronpedia

    INDEX
    Explanations

    structures resembling nested objects or configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ―――――
    -0.73
    شكرا
    -0.63
     doubtnut
    -0.63
     يتيمه
    -0.61
     itſelf
    -0.59
     ――――――――
    -0.59
     Sorgen
    -0.58
     stiefel
    -0.56
    Einf
    -0.55
     Mahat
    -0.55
    POSITIVE LOGITS
     {
    2.74
     {
    2.04
     {(
    1.59
     {\
    1.53
    ({
    1.33
     {[
    1.33
     \{
    1.31
    ={
    1.26
     ({
    1.25
     {-
    1.23
    Act Density 0.192%

    No Known Activations