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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey anticipation or prediction regarding future events or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istros
    -0.16
    ikal
    -0.15
    essler
    -0.15
    ic
    -0.15
    upal
    -0.15
    adel
    -0.15
    mbH
    -0.14
    esine
    -0.14
    phinx
    -0.14
    quist
    -0.14
    POSITIVE LOGITS
    orate
    0.23
    antly
    0.19
    ably
    0.19
    oe
    0.18
    ingly
    0.17
    entially
    0.16
    ose
    0.15
     expect
    0.15
    olit
    0.15
     Expect
    0.14
    Act Density 0.053%

    No Known Activations