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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to compilation and programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bulldogs
    -0.72
    (!__
    -0.69
    økt
    -0.67
    EndTag
    -0.67
    iriman
    -0.67
    Geplaatst
    -0.65
    ibição
    -0.64
     Jule
    -0.62
    ekte
    -0.61
    sailor
    -0.61
    POSITIVE LOGITS
    Comp
    2.90
     Comp
    2.90
     comp
    2.80
    comp
    2.74
     COMP
    2.47
    COMP
    2.44
     comps
    2.20
    comps
    1.78
     COM
    1.67
    COM
    1.65
    Act Density 0.115%

    No Known Activations