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

    Neuronpedia

    INDEX
    Explanations

    mentions of robots or automated systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ining
    -0.16
    icast
    -0.15
     once
    -0.15
     overall
    -0.14
    ãĥ¼ãĤ¹
    -0.14
    avaÅŁ
    -0.14
    ibel
    -0.13
    aring
    -0.13
    erg
    -0.13
    ple
    -0.13
    POSITIVE LOGITS
    ãģıãĤī
    0.16
    OLEAN
    0.15
    arium
    0.15
    ÌĤ
    0.15
    ERV
    0.14
    rchive
    0.14
    acle
    0.14
    alaxy
    0.14
    aptcha
    0.14
    nev
    0.14
    Act Density 0.001%

    No Known Activations