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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ger"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ccording
    -0.67
    ensions
    -0.65
    ension
    -0.64
    irection
    -0.63
    Copyright
    -0.62
     Virtue
    -0.60
    erest
    -0.59
    iversal
    -0.58
     stagnation
    -0.58
    san
    -0.57
    POSITIVE LOGITS
    vous
    0.82
    adish
    0.81
    geist
    0.80
    gers
    0.80
    GER
    0.77
    ger
    0.76
    rants
    0.73
    poon
    0.73
    ravity
    0.72
    andom
    0.71
    Act Density 0.022%

    No Known Activations