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

    Neuronpedia

    INDEX
    Explanations

    phrases and words related to beginnings, origins, and the start of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate emergence or creation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     quint
    -0.65
    isc
    -0.63
    rouse
    -0.61
     misunderstood
    -0.61
    ider
    -0.60
    ucket
    -0.59
     Bucket
    -0.58
    isine
    -0.58
    oken
    -0.57
     eccentric
    -0.57
    POSITIVE LOGITS
    enance
    0.84
    EEE
    0.80
    thood
    0.80
    runners
    0.72
    ãĥĹ
    0.70
    ãĤ¡
    0.69
    ãģ¦
    0.69
     à¤
    0.68
    ãĤ»
    0.68
    à¤
    0.67
    Act Density 0.063%

    No Known Activations