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

    Neuronpedia

    INDEX
    Explanations

    references to actions of dropping or leaving things behind

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abr
    -0.06
    ij¸
    -0.06
    uries
    -0.06
    leness
    -0.06
     Auch
    -0.06
     success
    -0.06
    uish
    -0.06
    zin
    -0.05
    xious
    -0.05
    (clock
    -0.05
    POSITIVE LOGITS
    -drop
    0.11
     dropped
    0.11
     dropping
    0.11
    (drop
    0.10
     drops
    0.10
     drop
    0.10
    .drop
    0.10
     Drop
    0.10
     onto
    0.10
    DROP
    0.10
    Act Density 0.021%

    No Known Activations