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

    Neuronpedia

    INDEX
    Explanations

    contractions of "is"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that contain the word "there's."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    velop
    -0.85
    shire
    -0.74
    rence
    -0.69
    IENT
    -0.65
    planet
    -0.64
    oint
    -0.63
    ller
    -0.62
    cil
    -0.61
    360
    -0.59
    ject
    -0.59
    POSITIVE LOGITS
     gotta
    1.29
     gonna
    1.14
     got
    0.90
     been
    0.89
    pace
    0.76
     Been
    0.73
    ELF
    0.72
    been
    0.72
     gotten
    0.71
    soDeliveryDate
    0.70
    Act Density 0.067%

    No Known Activations