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

    Neuronpedia

    INDEX
    Explanations

    phrases that discuss the act of leaving or abandonment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hers
    -0.18
    uya
    -0.16
    ácil
    -0.15
    metro
    -0.15
     FLAG
    -0.15
    dued
    -0.14
    rna
    -0.14
     KUR
    -0.14
    eriod
    -0.14
    mux
    -0.14
    POSITIVE LOGITS
     behind
    0.22
     room
    0.20
     Behind
    0.19
    Behind
    0.17
     Room
    0.16
    beh
    0.16
    enschaft
    0.15
    room
    0.15
     footprint
    0.15
    омÑĸ
    0.15
    Act Density 0.077%

    No Known Activations