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

    Neuronpedia

    INDEX
    Explanations

    pronouns related to gender in the context of personal references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    +#+
    -0.83
     nakalista
    -0.79
    IntoConstraints
    -0.78
    Rhestr
    -0.75
    ]")]
    -0.71
    DockStyle
    -0.70
    sizeCache
    -0.69
     الاطلاع
    -0.69
     intptr
    -0.67
    adaptiveStyles
    -0.66
    POSITIVE LOGITS
    টি
    0.51
    key
    0.49
    фициальный
    0.48
     or
    0.47
     或
    0.46
     '<?
    0.45
    adpleegd
    0.44
     bądź
    0.44
    Ter
    0.43
     bzw
    0.43
    Act Density 0.254%

    No Known Activations