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

    Neuronpedia

    INDEX
    Explanations

    negations and terms related to limitations or exclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .Mesh
    -0.17
     Musical
    -0.16
     Messi
    -0.15
    orman
    -0.15
    (Media
    -0.15
    multiline
    -0.15
     Mesh
    -0.15
     MsgBox
    -0.15
    ÙĦت
    -0.15
    (Mod
    -0.15
    POSITIVE LOGITS
     matter
    0.73
    matter
    0.64
     Matter
    0.57
     matt
    0.55
     matters
    0.52
     mater
    0.52
     MAT
    0.50
     matte
    0.49
     mat
    0.45
     Matters
    0.40
    Act Density 0.073%

    No Known Activations