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

    Neuronpedia

    INDEX
    Explanations

    verbs related to causing influence or change

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving the concept of bringing or resulting in something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uary
    -0.73
    livious
    -0.71
    dating
    -0.69
    schild
    -0.68
    debian
    -0.67
    taker
    -0.66
    imon
    -0.66
    raid
    -0.64
    unker
    -0.63
    rant
    -0.61
    POSITIVE LOGITS
     forth
    1.25
     together
    0.92
     attention
    0.85
     forward
    0.83
     smiles
    0.77
     up
    0.75
    hurst
    0.72
     down
    0.70
     awareness
    0.70
    unity
    0.70
    Act Density 0.040%

    No Known Activations