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

    Neuronpedia

    INDEX
    Explanations

    thematic contrasts and statements about identity or absence of belief

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antMatchers
    -0.56
    ########.
    -0.56
    וויק
    -0.54
    }))
    -0.54
     estekak
    -0.52
    #+#
    -0.52
     ويكيپيديا
    -0.51
     Aristi
    -0.50
     Himo
    -0.50
     jScrollPane
    -0.49
    POSITIVE LOGITS
     unlike
    0.85
    unlike
    0.79
     avoid
    0.78
    RTLR
    0.77
    avoid
    0.75
     avoiding
    0.74
     avoided
    0.72
     NOT
    0.72
    Unlike
    0.71
     contrary
    0.71
    Act Density 0.382%

    No Known Activations