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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word 'here'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sw
    -0.63
    τητα
    -0.61
    sten
    -0.59
    cy
    -0.59
    ly
    -0.57
    st
    -0.57
    dom
    -0.57
    ts
    -0.57
    mo
    -0.56
    )");
    -0.56
    POSITIVE LOGITS
     here
    1.44
     aici
    1.31
     aqui
    1.22
     HERE
    1.19
     aquí
    1.16
    HERE
    1.15
     tää
    1.14
    here
    1.13
     здесь
    1.09
     כאן
    1.05
    Act Density 0.098%

    No Known Activations