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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "follow."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     follow
    -1.68
     Follow
    -1.48
    Follow
    -1.45
    follow
    -1.41
     FOLLOW
    -1.28
     follows
    -1.19
     followup
    -1.13
    FOLLOW
    -1.07
     Follows
    -1.05
    follows
    -0.95
    POSITIVE LOGITS
     nahilalakip
    0.63
    قایناقلار
    0.44
    RUnlock
    0.43
    wieś
    0.41
    ernalia
    0.41
    enderror
    0.40
    什么样的
    0.39
     ecológica
    0.39
    reduced
    0.38
    rungsseite
    0.38
    Act Density 0.007%

    No Known Activations