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
     connection
    -0.19
     Connection
    -0.17
    .connection
    -0.17
    connection
    -0.16
    order
    -0.15
    Connection
    -0.15
     connexion
    -0.15
     conjunction
    -0.14
    Codes
    -0.14
    jem
    -0.13
    POSITIVE LOGITS
     scope
    0.31
     terms
    0.30
     nature
    0.30
     scale
    0.25
     size
    0.25
     appearance
    0.24
     tone
    0.24
     content
    0.24
     outlook
    0.23
     term
    0.23
    Act Density 0.135%

    No Known Activations