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

    Neuronpedia

    INDEX
    Explanations

    the presence of double quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    the use of quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     killers
    -0.74
     hypothal
    -0.72
     Prim
    -0.71
     tabloid
    -0.71
     arri
    -0.71
     deterrent
    -0.70
     vigil
    -0.69
     cancell
    -0.69
     HDL
    -0.66
     disciplinary
    -0.66
    POSITIVE LOGITS
    true
    1.31
    yes
    1.30
    false
    1.25
    fuck
    1.17
    someone
    1.16
    nothing
    1.15
    every
    1.14
    SELECT
    1.14
    NOT
    1.13
    external
    1.13
    Act Density 0.101%

    No Known Activations