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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions or processes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to technology and its impact on human behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éŃĶ
    -0.65
    appa
    -0.64
    çĶ°
    -0.60
    Ĥİ
    -0.60
    yssey
    -0.60
    utenberg
    -0.59
    iland
    -0.58
    catentry
    -0.57
    é¾į
    -0.57
    iHUD
    -0.56
    POSITIVE LOGITS
     anymore
    1.98
     nor
    1.72
     necessarily
    1.39
     whatsoever
    1.31
     anywhere
    1.27
     anything
    1.19
     unless
    1.18
     overtly
    1.12
     anybody
    1.10
     terribly
    1.10
    Act Density 0.594%

    No Known Activations