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

    Neuronpedia

    INDEX
    Explanations

    terms related to mathematical expressions and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    angan
    -0.15
    BUM
    -0.15
    qe
    -0.15
    ewan
    -0.14
     invalidate
    -0.14
    oh
    -0.14
    ahn
    -0.14
    alis
    -0.14
    uo
    -0.14
    ahir
    -0.14
    POSITIVE LOGITS
    bindings
    0.15
    .scalablytyped
    0.14
    hood
    0.14
    reader
    0.14
    ants
    0.14
     odak
    0.14
    -reader
    0.14
    ousand
    0.14
    ledo
    0.13
    &R
    0.13
    Act Density 0.063%

    No Known Activations