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

    Neuronpedia

    INDEX
    Explanations

    references to a specific hotel chain

    oai_token-act-pair · gpt-3.5-turbo

    references to a particular establishment or brand-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     WARN
    -0.69
    theless
    -0.67
    ãģį
    -0.67
     Miko
    -0.66
    interstitial
    -0.65
    Interstitial
    -0.64
    xual
    -0.63
    pta
    -0.63
    holder
    -0.62
    scl
    -0.61
    POSITIVE LOGITS
    ivated
    1.27
    ivation
    1.25
    ivating
    1.07
    ographed
    0.98
    ör
    0.97
    oto
    0.95
    ificent
    0.94
    itious
    0.93
    ility
    0.91
    oring
    0.91
    Act Density 0.027%

    No Known Activations