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

    Neuronpedia

    INDEX
    Explanations

    phrases related to various methods and techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    teen
    -0.20
    wig
    -0.17
    ri
    -0.16
    /down
    -0.16
    deen
    -0.16
    ako
    -0.16
    unge
    -0.15
    recht
    -0.15
    VERTISE
    -0.15
    cat
    -0.15
    POSITIVE LOGITS
    ologies
    0.21
    ological
    0.21
     latter
    0.21
    anical
    0.20
    ology
    0.19
    ologi
    0.18
     Learned
    0.18
     learned
    0.17
    ologie
    0.17
    ologia
    0.17
    Act Density 0.016%

    No Known Activations