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

    Neuronpedia

    INDEX
    Explanations

    phrases related to linearity or straightness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Infórmanos
    -0.91
    Demografia
    -0.77
     createSprite
    -0.75
    LabelTagHelper
    -0.74
     Picchu
    -0.72
    çalves
    -0.71
    aarrggbb
    -0.70
    ity
    -0.69
     Hilo
    -0.69
    lamino
    -0.69
    POSITIVE LOGITS
     Bradshaw
    0.88
    Straight
    0.85
    straight
    0.84
    AFE
    0.83
     Straight
    0.83
     STRA
    0.82
     straight
    0.80
     Arabian
    0.79
     Siamese
    0.77
     Josie
    0.76
    Act Density 0.148%

    No Known Activations