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

    Neuronpedia

    INDEX
    Explanations

    references to confessions or admissions of guilt

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

    confessed, confession, confess

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bari
    -0.50
     Iva
    -0.49
    urlpatterns
    -0.49
    Toole
    -0.47
     tamp
    -0.45
     Silverstone
    -0.44
    بالإنجليزية
    -0.44
     Timmy
    -0.43
     Aro
    -0.43
     Timp
    -0.43
    POSITIVE LOGITS
     confession
    1.56
     confess
    1.50
     confessed
    1.47
     confesses
    1.45
     Confession
    1.39
     confessions
    1.30
     confes
    1.24
     Confessions
    1.09
    告白
    0.84
     déclaration
    0.63
    Act Density 0.005%

    No Known Activations