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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific values or states related to metrics or measures in a statistical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unc
    -0.19
    9
    -0.17
    BC
    -0.17
    7
    -0.17
    51
    -0.16
    25
    -0.16
    Ki
    -0.16
     Leon
    -0.16
    iej
    -0.16
    qui
    -0.15
    POSITIVE LOGITS
    ende
    0.30
    dda
    0.29
    tt
    0.28
    rs
    0.27
    ttp
    0.27
    rd
    0.26
    ckt
    0.26
    ntag
    0.25
    ttl
    0.24
    dd
    0.24
    Act Density 0.035%

    No Known Activations