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

    Neuronpedia

    INDEX
    Explanations

    references to external situations or entities outside a defined scope

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WriteTagHelper
    -0.71
    EMAS
    -0.56
     distanciation
    -0.56
    gonic
    -0.55
    orious
    -0.55
    rinha
    -0.53
     Cliffs
    -0.51
    werth
    -0.51
    RepeatedField
    -0.50
    derry
    -0.50
    POSITIVE LOGITS
    AndEndTag
    0.87
    存于互联网档案馆
    0.70
     beyond
    0.68
    enumi
    0.68
    Beyond
    0.68
     Beyond
    0.67
    enumii
    0.65
     dehors
    0.65
    Outside
    0.62
    beyond
    0.61
    Act Density 0.327%

    No Known Activations