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

    Neuronpedia

    INDEX
    Explanations

    invitations for feedback and opinions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ö¼
    -0.70
    agall
    -0.65
    ãĤ©
    -0.61
     Huang
    -0.60
    iral
    -0.60
    Traditional
    -0.59
    alsh
    -0.59
    ¥µ
    -0.59
    ortality
    -0.59
    Imm
    -0.59
    POSITIVE LOGITS
     feedback
    1.10
     suggestions
    1.09
     comments
    1.04
    comments
    1.03
     Feedback
    1.02
     Comments
    1.01
     sugg
    0.99
     comment
    0.98
     bookmark
    0.95
     Comment
    0.91
    Act Density 1.740%

    No Known Activations