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

    Neuronpedia

    INDEX
    Explanations

    technical or scientific terms and proposals

    oai_token-act-pair · gpt-3.5-turbo

    specific information related to proposals or definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     *)
    -0.62
     depends
    -0.61
    )*
    -0.60
    )"
    -0.56
    *)
    -0.53
    )'
    -0.53
     ?)
    -0.49
    '),
    -0.49
     meanwhile
    -0.49
    )?
    -0.49
    POSITIVE LOGITS
     unsuspecting
    0.50
     conflic
    0.48
    onto
    0.47
     prehistoric
    0.46
    ãĤ´ãĥ³
    0.46
    instead
    0.44
    abbit
    0.44
     ".
    0.43
    ãĥı
    0.43
     "#
    0.43
    Act Density 3.010%

    No Known Activations