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

    Neuronpedia

    INDEX
    Explanations

    words related to failure or flaws

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PerformLayout
    -0.67
     OBO
    -0.60
     незавершена
    -0.56
     FOREVER
    -0.54
    хьтан
    -0.53
    InsertCommand
    -0.52
     kone
    -0.51
     realizing
    -0.49
     jsPsych
    -0.49
     Tahoe
    -0.49
    POSITIVE LOGITS
     f
    2.38
     fumble
    0.82
     ff
    0.78
     getF
    0.74
    ｆ
    0.73
     ft
    0.72
     fl
    0.72
     ƒ
    0.71
     flyers
    0.69
     fv
    0.68
    Act Density 0.111%

    No Known Activations