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

    Neuronpedia

    INDEX
    Explanations

    phrases related to discussing or exploring the reasons behind the quality or uniqueness of a particular subject

    oai_token-act-pair · gpt-3.5-turbo

    phrases or questions about what constitutes quality or distinctiveness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nery
    -0.68
    nec
    -0.68
    Sov
    -0.68
    loader
    -0.67
    imation
    -0.66
    ima
    -0.65
    jury
    -0.63
    usterity
    -0.62
    ALTH
    -0.61
    imm
    -0.59
    POSITIVE LOGITS
     them
    0.90
     him
    0.84
     us
    0.84
     these
    0.78
     me
    0.76
     this
    0.71
     distinguishes
    0.66
     THEM
    0.65
     people
    0.62
     distinguish
    0.61
    Act Density 0.078%

    No Known Activations