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

    Neuronpedia

    INDEX
    Explanations

    statements of clarity or assertions regarding explanations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Haut
    -0.19
    ddy
    -0.16
    ideo
    -0.15
     Ard
    -0.15
    undry
    -0.15
    amas
    -0.14
    cimal
    -0.14
    IDEO
    -0.14
    λÏĮγ
    -0.14
    ikel
    -0.14
    POSITIVE LOGITS
     natural
    0.24
    natural
    0.22
     immediate
    0.21
     Natural
    0.20
    straight
    0.20
    atural
    0.18
    Natural
    0.18
    Straight
    0.18
     straight
    0.17
    tempt
    0.17
    Act Density 0.052%

    No Known Activations