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

    Neuronpedia

    INDEX
    Explanations

    statements about political opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.69
     Walkover
    -0.68
    igshid
    -0.66
    mybatisplus
    -0.65
     délib
    -0.65
    irão
    -0.65
    참고
    -0.63
     חיצוניים
    -0.60
    Referencies
    -0.60
    InjectAttribute
    -0.60
    POSITIVE LOGITS
     very
    0.53
     beautiful
    0.52
    very
    0.51
    очень
    0.50
    Very
    0.49
    beautiful
    0.49
     '\\;'
    0.49
     DAS
    0.45
     great
    0.45
    })()
    0.44
    Act Density 0.063%

    No Known Activations