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

    Neuronpedia

    INDEX
    Explanations

    symbols or quotation marks used in textual references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    úsqueda
    -0.17
    rac
    -0.16
    ning
    -0.15
    -urlencoded
    -0.15
    fold
    -0.15
    ch
    -0.15
    ami
    -0.14
    combe
    -0.14
    pipe
    -0.14
    vie
    -0.14
    POSITIVE LOGITS
    TY
    0.16
    zeug
    0.15
    ty
    0.15
    Å¡en
    0.15
    AndPassword
    0.15
    ãģĤãĤĬ
    0.15
    tails
    0.15
    erie
    0.15
    ÅĽci
    0.15
    ufe
    0.14
    Act Density 0.073%

    No Known Activations