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

    Neuronpedia

    INDEX
    Explanations

    phrases related to proving or demonstrating something

    oai_token-act-pair · gpt-3.5-turbo

    phrases relating to talent or skill recognition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     References
    -0.64
     Rape
    -0.62
    stab
    -0.62
     Lent
    -0.59
     raping
    -0.58
    intensive
    -0.57
    stocks
    -0.57
     Edited
    -0.56
    lihood
    -0.56
    figure
    -0.55
    POSITIVE LOGITS
     accordingly
    0.95
     exception
    0.84
     remedy
    0.74
    empl
    0.73
    olk
    0.73
     such
    0.72
    example
    0.72
    Thankfully
    0.69
    burgh
    0.69
    AMI
    0.69
    Act Density 1.110%

    No Known Activations