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

    Neuronpedia

    INDEX
    Explanations

    nouns and phrases related to events and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oby
    -0.17
    /stdc
    -0.15
    "struct
    -0.15
    eyle
    -0.15
    -Clause
    -0.15
    roje
    -0.15
    sik
    -0.14
    tÃŃ
    -0.14
    ÂłÐIJ
    -0.14
    eson
    -0.14
    POSITIVE LOGITS
    are
    0.15
     Hearts
    0.15
    aul
    0.15
    ]
    0.14
    vec
    0.13
    ↵
    0.13
    vero
    0.13
     ad
    0.13
    omi
    0.13
    ::
    0.12
    Act Density 0.094%

    No Known Activations