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

    Neuronpedia

    INDEX
    Explanations

    websites and social media handles

    oai_token-act-pair · gpt-3.5-turbo

    URLs and website references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Scheme
    -0.91
     Tone
    -0.90
     Singer
    -0.88
     Socket
    -0.87
     Fault
    -0.86
     Strikes
    -0.86
     Scale
    -0.85
     Hearts
    -0.85
     Tenth
    -0.84
     Rye
    -0.84
    POSITIVE LOGITS
    podcast
    1.26
    pod
    1.13
    _
    1.12
    official
    1.10
    music
    1.10
    movie
    1.09
    project
    1.09
    politics
    1.08
    beaut
    1.07
    facts
    1.07
    Act Density 0.174%

    No Known Activations