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

    Neuronpedia

    INDEX
    Explanations

    references to specific actions or entities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucu
    -0.17
    shima
    -0.16
    ůst
    -0.15
     PROT
    -0.14
    artz
    -0.14
     Highway
    -0.14
    istros
    -0.14
    pras
    -0.14
    olith
    -0.13
    ancer
    -0.13
    POSITIVE LOGITS
    del
    0.18
    -del
    0.17
     Horn
    0.17
     del
    0.16
    emark
    0.16
     Rest
    0.15
     em
    0.15
     rest
    0.15
    izik
    0.15
    çķª
    0.15
    Act Density 0.005%

    No Known Activations