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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a purpose or intention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    º
    -0.15
    opis
    -0.14
    ORMAT
    -0.14
    λεί
    -0.14
     sembl
    -0.14
    igu
    -0.13
    dad
    -0.13
    erten
    -0.13
    970
    -0.13
    hop
    -0.13
    POSITIVE LOGITS
    ges
    0.20
     purposes
    0.18
     unto
    0.16
    amina
    0.16
    uyla
    0.16
    INED
    0.15
     sake
    0.15
    oble
    0.15
    ged
    0.15
     reasons
    0.15
    Act Density 0.259%

    No Known Activations