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

    Neuronpedia

    INDEX
    Explanations

    references to academic citations or mathematical notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    196
    -0.20
    197
    -0.17
    199
    -0.17
    198
    -0.16
    195
    -0.15
    -Pack
    -0.15
    arters
    -0.14
    194
    -0.14
    zilla
    -0.14
    rvine
    -0.14
    POSITIVE LOGITS
     upcoming
    0.15
     forthcoming
    0.15
    201
    0.14
     Ay
    0.13
     ic
    0.13
     ab
    0.13
     Zhou
    0.13
     contextual
    0.13
     me
    0.13
     Namespace
    0.13
    Act Density 0.069%

    No Known Activations