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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditional or preceding circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding verbs

    np_acts-logits-general · gemini-2.0-flash

    before some action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.65
     chi̍t
    -0.64
    kept
    -0.61
     zů
    -0.59
    sequently
    -0.58
     bleef
    -0.58
     blieb
    -0.57
     instantaneous
    -0.57
    quickly
    -0.57
    లాలు
    -0.57
    POSITIVE LOGITS
     decide
    0.84
     officially
    0.83
     formally
    0.79
     fully
    0.77
     finalize
    0.76
     endgül
    0.76
    真正
    0.72
     finalized
    0.70
     decides
    0.70
     official
    0.68
    Act Density 0.324%

    No Known Activations