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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific identifiers or names related to datasets or entities in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     незавершена
    -0.61
     gynhyrchwyd
    -0.58
    OMET
    -0.57
    thasone
    -0.53
     Stoff
    -0.52
    ereum
    -0.52
     Claudius
    -0.51
     Cornelia
    -0.51
     Neb
    -0.51
     fleets
    -0.50
    POSITIVE LOGITS
     sa
    1.01
    sa
    0.92
    Sa
    0.92
     Sa
    0.88
     SA
    0.77
    SA
    0.76
     SAK
    0.73
    SAM
    0.72
    makeConstraints
    0.71
     tartalomajánló
    0.69
    Act Density 2.876%

    No Known Activations