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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    原始内容存档于
    -0.86
    ValueStyle
    -0.83
    mybatisplus
    -0.81
    antMatchers
    -0.79
    pushFollow
    -0.76
    twimg
    -0.74
     استنادى
    -0.74
     Infórmanos
    -0.73
    expandindo
    -0.72
    קישורים
    -0.71
    POSITIVE LOGITS
     ellip
    0.61
    ScreenState
    0.53
     tfsi
    0.51
     period
    0.49
    生平
    0.49
    RemoteException
    0.49
     Rek
    0.49
     ftu
    0.49
     Efq
    0.48
    TestBed
    0.48
    Act Density 0.874%

    No Known Activations