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

    Neuronpedia

    INDEX
    Explanations

    phrases related to hosting or being a host

    oai_token-act-pair · gpt-3.5-turbo

    references to hosts or hosting entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rite
    -0.68
     Dup
    -0.67
     Oval
    -0.62
    displayText
    -0.60
     Mills
    -0.60
     Schne
    -0.58
     skating
    -0.58
     Bleach
    -0.57
    zb
    -0.57
     Yard
    -0.57
    POSITIVE LOGITS
    esses
    1.39
    ess
    1.30
    ilities
    1.21
    ility
    1.20
    name
    1.15
    el
    1.13
    ile
    1.12
    names
    1.09
    iles
    1.03
    els
    1.03
    Act Density 0.051%

    No Known Activations