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

    Neuronpedia

    INDEX
    Explanations

    complex sentence structures and direct speech within dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipo
    -0.14
    ovacÃŃ
    -0.14
    पत
    -0.14
     reversed
    -0.14
    ichert
    -0.13
    oney
    -0.13
     enclosing
    -0.13
     hindsight
    -0.13
    ovi
    -0.13
    ιÏĥ
    -0.13
    POSITIVE LOGITS
     interrupt
    0.36
     interruption
    0.34
    interrupt
    0.33
     INTERRU
    0.32
     interruptions
    0.32
     Interrupt
    0.31
    Interrupt
    0.29
     interrupts
    0.28
     interrupted
    0.24
     Interr
    0.24
    Act Density 0.316%

    No Known Activations