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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "Int" followed by a number, possibly related to international or intelligence contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to "Int" or related terms in various contexts, likely indicating subjects related to intelligence or international matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gleaming
    -0.79
    ¶ħ
    -0.77
    jriwal
    -0.70
    76561
    -0.70
    wordpress
    -0.69
    llah
    -0.69
    yards
    -0.68
    姫
    -0.67
    éĹĺ
    -0.67
    artifacts
    -0.67
    POSITIVE LOGITS
    ellect
    1.32
    ensity
    1.31
    ention
    1.29
    ensive
    1.23
    uitive
    1.23
    estinal
    1.19
    ENTION
    1.13
    elligence
    1.07
    ellig
    0.99
    ensions
    0.97
    Act Density 0.015%

    No Known Activations