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

    Neuronpedia

    INDEX
    Explanations

    numerical values and measurements

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating possession or the existence of an entity or situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     herself
    -0.68
    soever
    -0.65
    iar
    -0.64
    hee
    -0.64
    PLIED
    -0.63
    Activ
    -0.63
    TE
    -0.63
    imo
    -0.62
    Fuel
    -0.62
    other
    -0.61
    POSITIVE LOGITS
     ourselves
    1.10
    htaking
    0.78
     glimpse
    0.75
     opportunity
    0.74
     "$:/
    0.72
    enhagen
    0.66
     beginnings
    0.65
     HUGE
    0.65
    zb
    0.63
    ideon
    0.63
    Act Density 0.406%

    No Known Activations