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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and specific numeric references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ôi
    -0.14
    ycz
    -0.14
    /GL
    -0.14
    _ABI
    -0.13
    ......
    -0.13
    cak
    -0.13
    abilia
    -0.13
    ulos
    -0.13
    ......↵↵
    -0.12
    '&&
    -0.12
    POSITIVE LOGITS
     Douglas
    0.37
    Dou
    0.30
     Hitch
    0.25
     dou
    0.24
     Adams
    0.23
     Dou
    0.21
     Doug
    0.21
     hitch
    0.20
     radio
    0.19
     Galaxy
    0.19
    Act Density 0.003%

    No Known Activations