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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns and related nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    their/her/his/my + noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -0.75
    uxxxx
    -0.66
    DIPSETTING
    -0.65
     CreateTagHelper
    -0.62
    :✨
    -0.61
    IntoConstraints
    -0.61
    ScopeManager
    -0.59
    tableFuture
    -0.59
    ^(@)
    -0.59
     indígen
    -0.58
    POSITIVE LOGITS
     efforts
    0.67
     predicament
    0.62
     findings
    0.58
     démarche
    0.56
     situation
    0.53
     success
    0.51
     plight
    0.49
     effort
    0.49
     endeavors
    0.48
     feat
    0.47
    Act Density 0.086%

    No Known Activations