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

    Neuronpedia

    INDEX
    Explanations

    phrases related to obstacles or starting points

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to obstacles or transitional phases in narratives or arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ngth
    -0.75
     weddings
    -0.71
    thood
    -0.68
    merce
    -0.67
    profits
    -0.63
    yss
    -0.63
     angered
    -0.63
    deen
    -0.63
     reviews
    -0.62
     hotels
    -0.62
    POSITIVE LOGITS
    lude
    0.85
     harb
    0.83
     hurdle
    0.79
    wark
    0.77
     point
    0.77
    starter
    0.76
    quel
    0.75
    brainer
    0.75
     obstacle
    0.75
    blow
    0.74
    Act Density 0.279%

    No Known Activations