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

    Neuronpedia

    INDEX
    Explanations

    HTML tags and code snippets

    oai_token-act-pair · gpt-3.5-turbo

    HTML tags and attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flu
    -0.76
     Bleach
    -0.68
     Baird
    -0.67
     Gors
    -0.64
     Democr
    -0.64
     Rogers
    -0.64
     Dynamics
    -0.63
     Brist
    -0.63
     Hastings
    -0.62
    atively
    -0.61
    POSITIVE LOGITS
    wcsstore
    1.15
    ="/
    0.85
    ":"/
    0.82
    picture
    0.79
    =/
    0.77
    ><
    0.76
    !--
    0.75
    usr
    0.74
    arag
    0.72
    division
    0.70
    Act Density 0.030%

    No Known Activations