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

    Neuronpedia

    INDEX
    Explanations

    words related to confirmation and validation of findings

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

    confirming findings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estekak
    -0.46
    Kanpo
    -0.44
     beginnetje
    -0.40
     szó
    -0.38
     InputDecoration
    -0.38
    Portály
    -0.38
     tour
    -0.38
     CanadaChoose
    -0.37
    agascar
    -0.37
    MessageOf
    -0.37
    POSITIVE LOGITS
     confirms
    0.88
     conferma
    0.80
     potwier
    0.79
     confirmer
    0.78
     affirms
    0.75
     confirme
    0.75
     confirming
    0.73
     confirm
    0.72
     bestätigt
    0.70
     bevestig
    0.69
    Act Density 0.048%

    No Known Activations