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

    Neuronpedia

    INDEX
    Explanations

    conditional statements or phrases that pose hypothetical scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ziel
    -0.17
    elig
    -0.16
    δά
    -0.15
    byn
    -0.15
     mou
    -0.14
    cribing
    -0.14
    ERGE
    -0.14
    alion
    -0.14
    inous
    -0.14
     Yao
    -0.13
    POSITIVE LOGITS
     playback
    0.23
    rame
    0.23
    rames
    0.23
     u
    0.23
     yes
    0.22
    ound
    0.21
    å¹²
    0.20
    rit
    0.20
    unny
    0.18
     possible
    0.18
    Act Density 0.123%

    No Known Activations