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

    Neuronpedia

    INDEX
    Explanations

    expressions of commitment and support in collaborative contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ§
    -0.15
    emean
    -0.15
    actly
    -0.14
    akin
    -0.14
     gul
    -0.14
    ãĥ¼ãĥĢ
    -0.14
     tut
    -0.14
    rowsable
    -0.14
    ÑĢÑıдÑĥ
    -0.13
    raquo
    -0.13
    POSITIVE LOGITS
     cannot
    0.20
    edo
    0.18
    æĹłæ³ķ
    0.17
    ụy
    0.16
     accept
    0.16
     prefer
    0.16
     accepts
    0.16
    accept
    0.15
     reserve
    0.15
    åģ¶
    0.15
    Act Density 0.122%

    No Known Activations