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

    Neuronpedia

    INDEX
    Explanations

    sources and citations in textual content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orman
    -0.16
    agn
    -0.16
    irm
    -0.15
    µľ
    -0.15
    ALCHEMY
    -0.15
    auce
    -0.14
    alysis
    -0.14
    iloc
    -0.14
    ÏĥÏĩ
    -0.14
    iani
    -0.14
    POSITIVE LOGITS
    rava
    0.15
    uilder
    0.15
    753
    0.14
    862
    0.14
     lash
    0.14
    поÑĢ
    0.14
    712
    0.14
     cap
    0.14
    Ut
    0.14
    nnen
    0.13
    Act Density 0.005%

    No Known Activations