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

    Neuronpedia

    INDEX
    Explanations

    words related to historical references or terms

    oai_token-act-pair · gpt-3.5-turbo

    specific suffixes and word endings in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    earable
    -0.67
    arted
    -0.65
    shown
    -0.65
    akespe
    -0.62
    sold
    -0.61
    nih
    -0.61
    furt
    -0.58
     Plum
    -0.58
    Downloadha
    -0.58
    sett
    -0.58
    POSITIVE LOGITS
     Echoes
    0.69
    Reloaded
    0.68
     Sunrise
    0.65
     charm
    0.65
     Revival
    0.62
    arious
    0.62
    vironment
    0.60
     Skies
    0.57
    osaurus
    0.55
    itas
    0.55
    Act Density 0.303%

    No Known Activations