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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "attach" and its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -ÑĤо
    -0.18
    ÑĢав
    -0.16
    stras
    -0.16
    rie
    -0.15
    erer
    -0.15
    stral
    -0.15
    stown
    -0.15
    570
    -0.15
    usal
    -0.15
    Equivalent
    -0.15
    POSITIVE LOGITS
    ments
    0.25
    ement
    0.23
    /embed
    0.22
    ements
    0.21
    é
    0.20
    -det
    0.19
    ment
    0.19
    Detach
    0.18
    ivity
    0.18
    .Attach
    0.17
    Act Density 0.023%

    No Known Activations