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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to acknowledgment and recognition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ernaut
    -0.16
    awa
    -0.16
    ież
    -0.15
     Rover
    -0.15
    erman
    -0.15
    ergarten
    -0.15
     Brennan
    -0.15
    itom
    -0.15
     erot
    -0.15
    ERSHEY
    -0.15
    POSITIVE LOGITS
    worthy
    0.27
    worth
    0.26
    ting
    0.21
    ration
    0.21
    ual
    0.20
    ric
    0.19
    ted
    0.18
    ional
    0.17
    ully
    0.17
    enance
    0.17
    Act Density 0.020%

    No Known Activations