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

    Neuronpedia

    INDEX
    Explanations

    references to strategic thinking and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ixel
    -0.15
    óż
    -0.15
    jal
    -0.15
    -translate
    -0.14
    egot
    -0.14
    linkplain
    -0.14
     заклад
    -0.14
     Dump
    -0.14
    -caret
    -0.14
    кÑĥл
    -0.14
    POSITIVE LOGITS
     knight
    0.28
     pawn
    0.28
     bishops
    0.28
     bishop
    0.27
     queens
    0.27
     ro
    0.26
     pieces
    0.25
     kings
    0.25
     Pawn
    0.24
     knights
    0.24
    Act Density 0.003%

    No Known Activations