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

    Neuronpedia

    INDEX
    Explanations

    references to political and economic terms, actions, and figures

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    theless
    -0.64
     Applicant
    -0.59
     scrut
    -0.53
     oneself
    -0.53
    \\\\\\\\
    -0.53
     Topic
    -0.51
     Dot
    -0.50
     Naz
    -0.50
    WARD
    -0.49
    ãĥ¼ãĥĨ
    -0.49
    POSITIVE LOGITS
    irs
    0.72
    ocratic
    0.64
    aughters
    0.64
    ultimate
    0.63
    own
    0.63
    uga
    0.62
    eenth
    0.62
    cient
    0.62
    ificant
    0.61
     counterparts
    0.61
    Act Density 10.537%

    No Known Activations