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

    Neuronpedia

    INDEX
    Explanations

    language or terms associated with deceitfulness or manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oir
    -0.18
    amu
    -0.16
    pk
    -0.16
    rossover
    -0.15
    kinson
    -0.15
    esson
    -0.14
     crossword
    -0.14
    èģļ
    -0.14
    ussen
    -0.14
    hlen
    -0.14
    POSITIVE LOGITS
     Hyde
    0.15
    ugins
    0.15
    HING
    0.15
    leDb
    0.15
     mang
    0.15
    ãĥ³ãĥĩãĤ£
    0.14
     kalk
    0.14
     Fundamental
    0.14
    odos
    0.14
    &T
    0.14
    Act Density 0.073%

    No Known Activations