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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a sense of obligation or duty

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to action and commitment toward a common goal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ©ãĥ³
    -0.83
    ĨĴ
    -0.71
    £ı
    -0.70
    ©¶æ
    -0.67
    ãĥ¯ãĥ³
    -0.66
    tyard
    -0.64
    Ľ
    -0.63
    hene
    -0.60
    ople
    -0.59
    orr
    -0.58
    POSITIVE LOGITS
     too
    2.22
     likewise
    1.59
    too
    1.40
     Too
    1.30
     ALSO
    1.08
     also
    1.07
     similarly
    1.04
     same
    0.92
    also
    0.91
     equally
    0.89
    Act Density 1.300%

    No Known Activations