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

    Neuronpedia

    INDEX
    Explanations

    phrases that invite further reading or continuation of a topic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lava
    -0.16
    lobber
    -0.16
    ocache
    -0.16
    aces
    -0.15
    VOKE
    -0.15
    krom
    -0.14
    ENG
    -0.14
    اخ
    -0.14
    intage
    -0.14
    ret
    -0.14
    POSITIVE LOGITS
     reading
    0.28
     Reading
    0.25
    Reading
    0.20
    _reading
    0.19
    .scalablytyped
    0.18
    èħ
    0.18
    reading
    0.17
    éĺħ读
    0.17
    996
    0.17
     Hang
    0.16
    Act Density 0.005%

    No Known Activations