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

    Neuronpedia

    INDEX
    Explanations

    references to loss, theft, or the protection of personal items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isay
    -0.18
     Marty
    -0.15
     collapsing
    -0.15
    _ISR
    -0.14
     Mickey
    -0.14
    lad
    -0.14
     skeletons
    -0.14
     coffin
    -0.14
     Sugar
    -0.13
    ỳ
    -0.13
    POSITIVE LOGITS
     lost
    0.35
     Lost
    0.33
    Lost
    0.33
    lost
    0.31
     misplaced
    0.27
    _lost
    0.25
     missing
    0.24
     perd
    0.23
    missing
    0.22
     loss
    0.22
    Act Density 0.070%

    No Known Activations