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

    Neuronpedia

    INDEX
    Explanations

    words related to gratitude and positive engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rocket
    -0.16
    Å¡el
    -0.15
    aba
    -0.15
    elter
    -0.15
    ead
    -0.15
    aled
    -0.14
    äl
    -0.14
    sut
    -0.14
    pcs
    -0.14
    put
    -0.14
    POSITIVE LOGITS
     Benn
    0.14
    Ïĥια
    0.13
    rection
    0.13
    ¯u
    0.13
    HeaderCode
    0.12
    ãĤ¤ãĤ¯
    0.12
    ãĤıãģĽ
    0.12
    .FILL
    0.12
    æī¬
    0.12
    ãĥ³ãĥĸ
    0.12
    Act Density 0.007%

    No Known Activations