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

    Neuronpedia

    INDEX
    Explanations

    references to interviews and discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    interviewer names spoken with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bcryptjs
    -0.50
     typelib
    -0.49
     createSprite
    -0.47
    subpackage
    -0.43
     avoient
    -0.39
     సౌకర్య
    -0.39
    hoeddwyd
    -0.38
    spender
    -0.37
    printStats
    -0.37
    पया
    -0.36
    POSITIVE LOGITS
     interviewers
    0.69
     interviewer
    0.69
    Interviewer
    0.63
     interviews
    0.57
     Interview
    0.54
     Interviews
    0.54
     entrevista
    0.54
     interviewed
    0.53
     entrevist
    0.53
     Piers
    0.52
    Act Density 0.057%

    No Known Activations