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

    Neuronpedia

    INDEX
    Explanations

    terms associated with performance metrics and outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ruba
    -0.16
    WillAppear
    -0.16
    embali
    -0.15
    .rdf
    -0.14
    InstanceOf
    -0.14
    jvu
    -0.14
    .ศ
    -0.14
    REC
    -0.14
    åģ
    -0.14
    .legend
    -0.13
    POSITIVE LOGITS
     until
    0.19
     followed
    0.17
     versus
    0.16
     Until
    0.16
    Until
    0.16
    893
    0.15
     vs
    0.15
    anan
    0.15
     Vs
    0.15
    oe
    0.14
    Act Density 0.021%

    No Known Activations