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

    Neuronpedia

    INDEX
    Explanations

    expressions related to needs, choices, and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     purpoſe
    -0.73
    sterious
    -0.67
     ſtate
    -0.65
    redients
    -0.60
     faſt
    -0.59
     leaſt
    -0.58
     Anſ
    -0.58
     uſe
    -0.57
    oray
    -0.56
     Jefus
    -0.56
    POSITIVE LOGITS
     oneself
    0.94
     InputDecoration
    0.78
     defaultstate
    0.74
    httphttps
    0.73
     يتيمه
    0.67
    AxisAlignment
    0.66
     BoxFit
    0.63
    InitVars
    0.63
    цездатний
    0.62
     CreateTagHelper
    0.62
    Act Density 0.134%

    No Known Activations