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

    Neuronpedia

    INDEX
    Explanations

    locations or places, particularly beaches

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Beach."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ativity
    -0.79
    selves
    -0.75
    phis
    -0.71
    perse
    -0.69
    ilyn
    -0.69
    utherford
    -0.68
    代
    -0.68
    IUM
    -0.66
    DIT
    -0.66
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -0.65
    POSITIVE LOGITS
     Resort
    0.92
     Gardens
    0.89
    goers
    0.86
     Splash
    0.86
     Beach
    0.84
    Lago
    0.80
     Boys
    0.78
    apon
    0.77
    tails
    0.76
     Boulevard
    0.75
    Act Density 0.011%

    No Known Activations