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

    Neuronpedia

    INDEX
    Explanations

    specific phrases or keywords encapsulating feelings or remarks that involve ethnic or racial identity

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and their context within quotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ²¾
    -0.87
    »Ĵ
    -0.66
    ¬¼
    -0.66
    anmar
    -0.65
    ãĥ¼ãĥĨãĤ£
    -0.63
    MpServer
    -0.63
    mber
    -0.62
    thora
    -0.62
    heed
    -0.61
    acas
    -0.61
    POSITIVE LOGITS
    /"
    1.11
     referring
    1.07
     meaning
    1.00
     implying
    0.96
     according
    0.89
     wherein
    0.85
     whereby
    0.82
     referencing
    0.82
     indicating
    0.81
    according
    0.80
    Act Density 0.063%

    No Known Activations