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

    Neuronpedia

    INDEX
    Explanations

    terms related to reduction or decrease in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fully
    -0.20
    ging
    -0.15
    overn
    -0.15
    fmt
    -0.14
    ump
    -0.14
    ieri
    -0.14
    itation
    -0.14
    ously
    -0.14
    aging
    -0.14
    pha
    -0.14
    POSITIVE LOGITS
    .scalablytyped
    0.24
    /remove
    0.21
    /rem
    0.20
    /null
    0.19
    ownt
    0.18
     thiá»ĥu
    0.18
    ToOne
    0.17
    çīĪ
    0.16
    uteur
    0.16
    /stretch
    0.16
    Act Density 0.042%

    No Known Activations