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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing the majority or significant portions in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    948
    -0.17
    åIJĦç§į
    -0.15
    æĭĶ
    -0.15
    á»į
    -0.15
    νια
    -0.14
    mouseup
    -0.14
    942
    -0.14
    اÛĮÙĩ
    -0.14
    AffineTransform
    -0.14
     Various
    -0.14
    POSITIVE LOGITS
     part
    0.31
     portion
    0.30
     parte
    0.28
     majority
    0.24
    /all
    0.24
     ÑĩаÑģÑĤÑĮ
    0.22
     portions
    0.21
    portion
    0.21
    part
    0.19
     chunk
    0.19
    Act Density 0.070%

    No Known Activations