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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social services and support for vulnerable populations

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions, particularly the word "and"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ixel
    -0.85
    rb
    -0.71
    gets
    -0.69
    ESH
    -0.68
    tera
    -0.65
    here
    -0.65
    mma
    -0.65
    ODY
    -0.65
    ight
    -0.64
    :(
    -0.64
    POSITIVE LOGITS
    etc
    1.00
     etc
    1.00
     assorted
    0.97
     carbohyd
    0.74
    ĪĴ
    0.73
     others
    0.68
     possibly
    0.64
     cooperative
    0.64
     other
    0.64
     redistributed
    0.63
    Act Density 0.245%

    No Known Activations