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

    Neuronpedia

    INDEX
    Explanations

    descriptions related to technical features or details

    oai_token-act-pair · gpt-3.5-turbo

    key elements and characteristics of systems or structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .</
    -0.79
     ÂŃ
    -0.72
    .''
    -0.67
    .")
    -0.67
    "/>
    -0.62
    ]."
    -0.61
    ."[
    -0.60
    "—
    -0.59
     thereto
    -0.59
     taxpayer
    -0.58
    POSITIVE LOGITS
    prisingly
    0.77
     however
    0.76
     meanwhile
    0.75
     Edit
    0.74
     POV
    0.68
     Alright
    0.63
     Hearth
    0.61
     Lets
    0.61
     furthermore
    0.60
     alot
    0.59
    Act Density 1.774%

    No Known Activations