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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing evaluations or judgments, particularly using intensity modifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulumi
    -0.18
    Ñıг
    -0.16
    swers
    -0.16
    ownik
    -0.16
    itti
    -0.16
    ãĥĹ
    -0.15
    awei
    -0.15
    ุà¸Ĺà¸ĺ
    -0.14
    DidChange
    -0.14
    fusc
    -0.14
    POSITIVE LOGITS
     glad
    0.22
     impressed
    0.20
     sure
    0.19
     tempted
    0.18
     worth
    0.17
     lots
    0.17
     pleased
    0.17
     convinced
    0.16
     true
    0.15
    onth
    0.15
    Act Density 0.238%

    No Known Activations