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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing exclusivity or singularity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     propia
    -0.54
     appena
    -0.51
     springfox
    -0.49
    aronder
    -0.49
     semplicemente
    -0.47
     vaikka
    -0.47
     simplemente
    -0.47
     tramonto
    -0.47
     própria
    -0.46
     rendus
    -0.46
    POSITIVE LOGITS
     remaining
    1.09
     thing
    1.04
    remaining
    0.99
     truly
    0.95
     exception
    0.91
     really
    0.88
     Remaining
    0.85
    truly
    0.84
     wirklich
    0.82
     véritable
    0.82
    Act Density 0.109%

    No Known Activations