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

    Neuronpedia

    INDEX
    Explanations

    phrases that introduce additional information or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sofar
    -0.20
     spite
    -0.18
    duct
    -0.16
    appropri
    -0.15
    ServletResponse
    -0.15
    ugu
    -0.14
    oca
    -0.14
    ducted
    -0.14
    ãĤ¤ãĤº
    -0.14
    alus
    -0.14
    POSITIVE LOGITS
     essence
    0.40
     short
    0.38
     fact
    0.32
     lay
    0.32
     effect
    0.31
     ess
    0.30
    short
    0.30
     other
    0.29
    -short
    0.28
     brief
    0.27
    Act Density 0.127%

    No Known Activations