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

    Neuronpedia

    INDEX
    Explanations

    references to anonymity and sensitive issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     èij
    -0.17
    oi
    -0.15
    342
    -0.15
    eward
    -0.15
     ^{°}
    -0.15
    ovaly
    -0.14
    बर
    -0.14
    uisine
    -0.14
    884
    -0.14
    имÑĥ
    -0.14
    POSITIVE LOGITS
     Anonymous
    0.18
    eva
    0.18
    anonymous
    0.18
     anonymously
    0.17
     anonymous
    0.16
     anonymity
    0.16
    Anonymous
    0.15
    gard
    0.15
    illez
    0.15
    antee
    0.15
    Act Density 0.016%

    No Known Activations