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

    Neuronpedia

    INDEX
    Explanations

    words related to health and assistance

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to education and support for students

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ³³³³
    -0.71
     !!
    -0.64
     ³³
    -0.64
    [/
    -0.63
    ³³
    -0.63
    ³³³
    -0.63
    ↵Âł
    -0.61
     Âł Âł Âł Âł Âł Âł Âł Âł
    -0.61
    ãĢ
    -0.60
     Whilst
    -0.60
    POSITIVE LOGITS
    their
    1.46
     themselves
    1.39
     their
    1.39
     theirs
    1.16
    Their
    1.15
     THEIR
    1.13
     they
    1.04
    they
    1.00
     Their
    0.99
    They
    0.93
    Act Density 1.033%

    No Known Activations