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

    Neuronpedia

    INDEX
    Explanations

    types of programming language constructs, such as functions and parameters

    oai_token-act-pair · gpt-3.5-turbo

    references to data types in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gul
    -0.86
    姫
    -0.75
    ILLE
    -0.74
    äºĶ
    -0.72
    aldi
    -0.71
    interstitial
    -0.70
    eor
    -0.69
    Leaks
    -0.68
    vous
    -0.67
    uckland
    -0.66
    POSITIVE LOGITS
    faces
    1.24
    face
    1.12
    casting
    1.07
    ahead
    1.00
    alias
    0.99
    etting
    0.93
    cast
    0.86
    classes
    0.84
     inference
    0.83
    etter
    0.79
    Act Density 0.016%

    No Known Activations