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

    Neuronpedia

    INDEX
    Explanations

    issues related to software functionality or errors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ourselves
    -0.17
     yourself
    -0.14
    ailable
    -0.14
    容æĺĵ
    -0.14
    åIJ§
    -0.14
    æĺĵ
    -0.14
    ìī
    -0.14
    ãģ§ãģĹãĤĩãģĨ
    -0.14
    าà¸Ļ
    -0.14
     YYS
    -0.13
    POSITIVE LOGITS
     weird
    0.21
     strange
    0.20
     instead
    0.19
     weir
    0.19
     seems
    0.19
    izarre
    0.19
     wrong
    0.18
     поÑĩемÑĥ
    0.18
     correct
    0.17
     console
    0.17
    Act Density 0.154%

    No Known Activations