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

    Neuronpedia

    INDEX
    Explanations

    titles and descriptors of creative works or publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olt
    -0.15
     relative
    -0.14
    Apart
    -0.14
    -now
    -0.14
     nowhere
    -0.14
     Apart
    -0.13
    idea
    -0.13
     aqu
    -0.13
    éł
    -0.13
    oft
    -0.13
    POSITIVE LOGITS
     reflections
    0.20
     Essays
    0.19
    Subtitle
    0.18
     докÑĥм
    0.18
     essays
    0.17
     Eine
    0.16
     notes
    0.15
    istrov
    0.15
     how
    0.15
     Rede
    0.15
    Act Density 0.064%

    No Known Activations