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

    Neuronpedia

    INDEX
    Explanations

    phrases related to statistical or mathematical measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     la
    -0.22
     il
    -0.16
     da
    -0.16
    eneg
    -0.15
    -tra
    -0.15
    份
    -0.15
    ENSE
    -0.15
     che
    -0.15
     si
    -0.14
    ftware
    -0.14
    POSITIVE LOGITS
    urn
    0.24
    resse
    0.23
    etro
    0.20
     front
    0.19
    abet
    0.18
    apos
    0.18
     cui
    0.18
    atrib
    0.17
     stamp
    0.17
    URN
    0.17
    Act Density 0.009%

    No Known Activations