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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating ability and permission

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IODevice
    -0.14
    acho
    -0.14
    apis
    -0.14
     بÙĪابة
    -0.14
    &D
    -0.13
    assertInstanceOf
    -0.13
    ighton
    -0.13
    ulton
    -0.13
    áb
    -0.13
    ogue
    -0.13
    POSITIVE LOGITS
     doing
    1.20
     Doing
    1.11
    doing
    1.07
    Doing
    1.05
    åģļ
    0.83
     done
    0.77
     do
    0.68
    done
    0.60
     did
    0.59
     does
    0.59
    Act Density 1.041%

    No Known Activations