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

    Neuronpedia

    INDEX
    Explanations

    instances of numerical values and their related context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    enumi
    -0.76
    igsaw
    -0.68
    phazard
    -0.68
    󠁢
    -0.67
     spade
    -0.66
    bestos
    -0.65
     Smiley
    -0.64
     arşivlendi
    -0.63
     smtplib
    -0.63
    bleven
    -0.63
    POSITIVE LOGITS
    Personendaten
    0.59
    UnusedPrivate
    0.56
    πουργ
    0.54
     <>",
    0.51
    RTHOOK
    0.50
     informée
    0.48
    EDEFAULT
    0.47
    Dea
    0.45
    ped
    0.45
    chuga
    0.44
    Act Density 0.008%

    No Known Activations