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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating unprecedented circumstances or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    γκ
    -0.15
    pus
    -0.15
    ocker
    -0.14
    hlen
    -0.14
     Leap
    -0.14
    ripp
    -0.14
     Leban
    -0.14
    adÃŃ
    -0.14
    mine
    -0.13
    dept
    -0.13
    POSITIVE LOGITS
     ever
    0.26
     previous
    0.24
     previously
    0.23
    -ever
    0.23
    previous
    0.21
    .previous
    0.20
     Previous
    0.19
     EVER
    0.18
    ever
    0.18
     Previously
    0.18
    Act Density 0.036%

    No Known Activations