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

    Neuronpedia

    INDEX
    Explanations

    phrases that compare qualities or attributes using superlatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tol
    -0.17
    _cpp
    -0.16
    ató
    -0.16
    chop
    -0.15
    achten
    -0.15
    å®ĺ
    -0.15
    enco
    -0.15
    æ¿
    -0.14
    inx
    -0.14
    enced
    -0.14
    POSITIVE LOGITS
     nor
    0.17
    crest
    0.15
    amps
    0.15
    epad
    0.14
    ops
    0.14
    hack
    0.14
    OPS
    0.14
    iá»ĥu
    0.13
    ee
    0.13
     Gree
    0.13
    Act Density 0.071%

    No Known Activations