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

    Neuronpedia

    INDEX
    Explanations

    words related to the publication or release of works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ergies
    -0.65
    ectoria
    -0.61
    -0.61
     <<<<<<<<<<<<<<
    -0.59
    ostom
    -0.58
     ब्रेकडाउन
    -0.57
    xxxxxxxxxxxxxxxx
    -0.55
    tikzpicture
    -0.55
    ArgsConstructor
    -0.54
    scription
    -0.53
    POSITIVE LOGITS
     released
    2.23
    released
    1.82
     Released
    1.75
    Released
    1.57
     published
    1.31
     issued
    1.31
     announced
    1.16
     RELE
    1.12
    published
    1.10
     unveiled
    1.10
    Act Density 0.143%

    No Known Activations