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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the frequency or pattern of usage of something in text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "usage" related to various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inosaur
    -0.75
    abella
    -0.69
    tell
    -0.68
    hair
    -0.61
     Kore
    -0.60
    bitious
    -0.59
     renal
    -0.59
     embry
    -0.57
     Barg
    -0.57
     Baghd
    -0.56
    POSITIVE LOGITS
     habits
    0.93
    iences
    0.82
     patterns
    0.76
    ername
    0.75
    icides
    0.72
    ites
    0.68
    itures
    0.68
    ality
    0.68
    ickr
    0.68
    ately
    0.67
    Act Density 0.027%

    No Known Activations