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

    Neuronpedia

    INDEX
    Explanations

    language related to equality and equivalence in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Portale
    -0.75
    "):
    -0.74
     Hanno
    -0.71
     يتيمه
    -0.71
    winston
    -0.70
    uride
    -0.69
     meste
    -0.68
     Vasili
    -0.68
    ]--;
    -0.66
    ":["
    -0.65
    POSITIVE LOGITS
     equal
    1.26
     equ
    1.14
     Equal
    1.14
    ('=
    1.13
     EQUAL
    1.12
    EQUAL
    1.12
     equals
    1.10
    equal
    1.10
    Equal
    1.09
     EQU
    1.06
    Act Density 0.133%

    No Known Activations