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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate uncertainty or caution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    andbox
    -0.18
     Weiner
    -0.16
    elter
    -0.15
    òa
    -0.15
    ROUT
    -0.15
    gos
    -0.15
     QMap
    -0.15
     IsNot
    -0.14
    izza
    -0.14
    nia
    -0.14
    POSITIVE LOGITS
    ||
    0.15
    ITERAL
    0.15
    vinc
    0.15
     Rena
    0.15
    notes
    0.15
     Twins
    0.15
     statt
    0.14
     figur
    0.14
    weg
    0.14
     Orient
    0.14
    Act Density 0.070%

    No Known Activations