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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Now" to indicate shifts in topic or tone

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ancell
    -0.16
    ntl
    -0.14
    nor
    -0.14
    ngör
    -0.14
    gne
    -0.14
    gba
    -0.14
    amel
    -0.13
    åĶ
    -0.13
    åIJ¦
    -0.13
    anness
    -0.13
    POSITIVE LOGITS
    here
    0.33
     comes
    0.25
     onto
    0.24
    adays
    0.23
    HERE
    0.22
     imagine
    0.21
    onto
    0.21
     Ont
    0.20
    onder
    0.19
     granted
    0.19
    Act Density 0.039%

    No Known Activations