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

    Neuronpedia

    INDEX
    Explanations

    references to the action of dropping or items that can be dropped

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    enumii
    -0.68
    anthene
    -0.68
     怎样
    -0.66
     acciaio
    -0.66
    zczegól
    -0.65
    AxisAlignment
    -0.61
    ]';
    -0.61
    TestTools
    -0.61
    ScopeManager
    -0.60
     contextLoads
    -0.60
    POSITIVE LOGITS
     drop
    1.66
    drop
    1.66
     DROP
    1.65
     drops
    1.63
     Drops
    1.59
     Drop
    1.58
    drops
    1.58
    Drop
    1.56
    DROP
    1.46
    DRO
    1.39
    Act Density 0.035%

    No Known Activations