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

    Neuronpedia

    INDEX
    Explanations

    expressions of admiration and positivity towards writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÏĥÏĦε
    -0.14
     assisting
    -0.14
    stery
    -0.14
    aira
    -0.14
    pb
    -0.13
    ุà¹ī
    -0.13
    ãĥĥãĤ¯
    -0.13
    verbatim
    -0.13
     private
    -0.13
    erts
    -0.13
    POSITIVE LOGITS
    ivery
    0.18
    ãĥ³ãĤ¬
    0.17
    åĪļæīį
    0.14
    NECT
    0.14
    utenberg
    0.14
    ubu
    0.14
    orte
    0.13
    лÑİд
    0.13
     noisy
    0.13
    dum
    0.13
    Act Density 0.062%

    No Known Activations