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

    Neuronpedia

    INDEX
    Explanations

    repeated instances of the word "Hop" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    divider
    -0.18
    hand
    -0.17
    aments
    -0.17
    tte
    -0.17
    ature
    -0.16
    aphore
    -0.15
    icator
    -0.15
    nder
    -0.15
    inner
    -0.15
     callee
    -0.15
    POSITIVE LOGITS
    kins
    0.24
    py
    0.24
    itals
    0.22
    croft
    0.21
    portunity
    0.20
    kinson
    0.19
    ital
    0.18
    Hop
    0.18
     Hop
    0.18
    inion
    0.17
    Act Density 0.010%

    No Known Activations