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

    Neuronpedia

    INDEX
    Explanations

    modes of progression or transitions in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FromClass
    -0.17
    ovel
    -0.16
    å¾ŀ
    -0.16
    /forum
    -0.15
    ãģĭãĤī
    -0.15
    zig
    -0.15
    avel
    -0.14
    ekler
    -0.14
    ãģ°
    -0.14
     från
    -0.14
    POSITIVE LOGITS
    /to
    0.38
     scratch
    0.25
    scratch
    0.21
    /by
    0.21
    /about
    0.21
     perspective
    0.19
     standpoint
    0.19
     whence
    0.18
    mers
    0.18
     within
    0.18
    Act Density 0.314%

    No Known Activations