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

    Neuronpedia

    INDEX
    Explanations

    phrases associated with performance metrics and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rosenberg
    -0.20
    issen
    -0.18
     diffs
    -0.16
    aset
    -0.15
     Sw
    -0.14
     Garrett
    -0.14
    ÐĤ
    -0.14
     diff
    -0.14
     Diff
    -0.13
    iclass
    -0.13
    POSITIVE LOGITS
    oire
    0.17
    ario
    0.16
    aign
    0.14
    ormsg
    0.14
    ighth
    0.14
    verity
    0.14
    acro
    0.14
    irt
    0.14
    hoa
    0.14
    oral
    0.14
    Act Density 0.015%

    No Known Activations