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

    Neuronpedia

    INDEX
    Explanations

    concepts related to comparison and value assessment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erner
    -0.15
    -translate
    -0.14
    jal
    -0.14
    кÑĥл
    -0.14
    ixel
    -0.14
    _failure
    -0.13
     Studio
    -0.13
    ubb
    -0.13
    flows
    -0.12
    å¥ij
    -0.12
    POSITIVE LOGITS
     bishop
    0.29
     knight
    0.29
     queens
    0.27
     bishops
    0.27
     knights
    0.26
     Bishop
    0.25
     pawn
    0.24
     Knight
    0.23
     kings
    0.23
     queen
    0.23
    Act Density 0.007%

    No Known Activations