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

    Neuronpedia

    INDEX
    Explanations

    pronouns and determiners related to the speaker or writer

    oai_token-act-pair · gpt-3.5-turbo

    pronouns indicating people or groups involved in actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idge
    -0.67
    geries
    -0.64
    math
    -0.63
     spoilers
    -0.59
    ³³³³
    -0.59
    endif
    -0.58
    vine
    -0.58
    quest
    -0.56
     inver
    -0.56
     unspecified
    -0.55
    POSITIVE LOGITS
    've
    0.83
     encountered
    0.81
     dreamed
    0.79
    'd
    0.77
     frequ
    0.75
     envisioned
    0.74
     currently
    0.72
     received
    0.71
     allotted
    0.71
     encounter
    0.70
    Act Density 0.134%

    No Known Activations