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

    Neuronpedia

    INDEX
    Explanations

    words indicating hesitation or uncertainty in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stal
    -0.15
     æ®
    -0.14
    è¿·
    -0.14
     Král
    -0.14
    .pg
    -0.14
    RunLoop
    -0.13
     acomp
    -0.13
    ashboard
    -0.13
     Einsatz
    -0.13
     Zd
    -0.13
    POSITIVE LOGITS
     Sims
    0.36
     sims
    0.36
     Sim
    0.28
    Sim
    0.25
     sim
    0.24
    .sim
    0.21
    sim
    0.21
     simmer
    0.20
     SIM
    0.18
    _sim
    0.18
    Act Density 0.007%

    No Known Activations