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

    Neuronpedia

    INDEX
    Explanations

    contractions in sentences

    oai_token-act-pair · gpt-3.5-turbo

    contractions referring to possessive or indicative phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imeter
    -0.68
    heid
    -0.67
    rawdownloadcloneembedreportprint
    -0.63
    ãĤ´ãĥ³
    -0.62
    icka
    -0.62
    estial
    -0.61
    estern
    -0.61
    ics
    -0.59
    imeters
    -0.59
    sch
    -0.57
    POSITIVE LOGITS
     why
    1.10
     okay
    0.98
    why
    0.96
     exactly
    0.90
     understandable
    0.90
     reflected
    0.89
     fine
    0.89
     precisely
    0.88
     OK
    0.83
     unacceptable
    0.82
    Act Density 0.086%

    No Known Activations