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

    Neuronpedia

    INDEX
    Explanations

    prepositions followed by a location or group identifier

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "in the" across different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rers
    -0.71
    ahime
    -0.70
    rer
    -0.67
    sem
    -0.66
    rar
    -0.64
    rig
    -0.63
    interstitial
    -0.62
    oother
    -0.62
    0000000000000000
    -0.62
    reements
    -0.62
    POSITIVE LOGITS
     imaginable
    0.97
    pires
    0.87
     existence
    0.83
     except
    0.82
    except
    0.80
     sight
    0.76
    soever
    0.75
     planet
    0.70
     Universe
    0.69
     goddamn
    0.69
    Act Density 0.193%

    No Known Activations