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

    Neuronpedia

    INDEX
    Explanations

    organization's names and events

    oai_token-act-pair · gpt-3.5-turbo

    suffixes commonly associated with nouns and verbs, particularly those ending in "or" and "er"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    !/
    -0.59
    avorite
    -0.58
     Advertisement
    -0.57
    REF
    -0.55
    upon
    -0.54
    é¾į
    -0.52
    姫
    -0.52
    Magikarp
    -0.51
    Ĥª
    -0.51
     antiv
    -0.51
    POSITIVE LOGITS
    ching
    0.92
    eness
    0.90
    cher
    0.80
    chers
    0.79
    ches
    0.76
    ched
    0.76
    oy
    0.72
    chery
    0.71
    eto
    0.71
    olith
    0.69
    Act Density 0.158%

    No Known Activations