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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "in" across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iance
    -0.15
    thing
    -0.14
     thing
    -0.14
    000
    -0.14
    ch
    -0.14
    32
    -0.14
     intptr
    -0.14
    jad
    -0.13
    iel
    -0.13
    f
    -0.13
    POSITIVE LOGITS
     scope
    0.28
     appearance
    0.25
     tone
    0.23
     outlook
    0.23
     content
    0.23
     nature
    0.21
     scale
    0.21
     execution
    0.20
     Scope
    0.20
     intent
    0.20
    Act Density 0.091%

    No Known Activations