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

    Neuronpedia

    INDEX
    Explanations

    certain words or phrases enclosed in quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    quoted phrases or dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     killers
    -0.77
     adjud
    -0.74
     cancell
    -0.74
     tabloid
    -0.72
     hypothal
    -0.70
     bases
    -0.70
     deterrent
    -0.70
     arri
    -0.69
     vigil
    -0.68
     buoy
    -0.68
    POSITIVE LOGITS
    true
    1.23
    yes
    1.19
    false
    1.19
    personal
    1.14
    someone
    1.13
    nothing
    1.08
    human
    1.07
    fuck
    1.06
    everything
    1.06
    every
    1.05
    Act Density 0.093%

    No Known Activations