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

    Neuronpedia

    INDEX
    Explanations

    phrases related to exploration and discovery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    statt
    -0.16
    eless
    -0.15
    ед
    -0.15
    TED
    -0.15
    emain
    -0.15
    dings
    -0.15
    enas
    -0.15
    eya
    -0.14
    ched
    -0.14
    owing
    -0.14
    POSITIVE LOGITS
     possibilities
    0.19
     whether
    0.17
     depths
    0.17
     ways
    0.17
     possibility
    0.16
     POSSIBILITY
    0.16
     options
    0.16
     minded
    0.16
    -minded
    0.16
    /options
    0.16
    Act Density 0.015%

    No Known Activations