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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing enjoyment or satisfaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /place
    -0.17
    HELL
    -0.15
    arra
    -0.15
    ovan
    -0.15
    aday
    -0.15
    els
    -0.15
    ellers
    -0.14
    oproject
    -0.14
    ispens
    -0.14
    ling
    -0.14
    POSITIVE LOGITS
    fully
    0.23
    ably
    0.19
    ful
    0.18
    ment
    0.18
    FULL
    0.17
    /dis
    0.17
    ABEL
    0.17
    ous
    0.17
    FUL
    0.16
    ร
    0.16
    Act Density 0.041%

    No Known Activations