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

    Neuronpedia

    INDEX
    Explanations

    elements related to HTML and coding structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ed
    -0.28
    ↵
    -0.23
    a
    -0.21
    y
    -0.21
    al
    -0.21
    e
    -0.20
    i
    -0.19
    c
    -0.19
    o
    -0.19
    d
    -0.18
    POSITIVE LOGITS
     !***
    0.20
    elli
    0.18
    ouch
    0.17
    -----------↵
    0.16
    ndef
    0.16
    _simps
    0.16
    ---------↵
    0.15
    ################################################################################↵
    0.15
    ropa
    0.15
    ellers
    0.15
    Act Density 0.163%

    No Known Activations