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

    Neuronpedia

    INDEX
    Explanations

    references to violence and its consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    >:</
    -0.16
     Ones
    -0.15
    >Nama
    -0.14
    ocio
    -0.14
    >Main
    -0.14
    LOPT
    -0.14
    >Lorem
    -0.14
    orra
    -0.14
     (~
    -0.13
    OnError
    -0.13
    POSITIVE LOGITS
     >
    0.52
    >
    0.46
     >↵
    0.34
    >NN
    0.32
     greater
    0.31
    >manual
    0.30
     >>
    0.29
    >(
    0.28
     >↵↵
    0.28
     ><
    0.28
    Act Density 0.033%

    No Known Activations