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

    Neuronpedia

    INDEX
    Explanations

    phrases and variations of the verb "to be" indicating existence or presence

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

    are plus a state or action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.79
     queſta
    -0.78
     defaultstate
    -0.75
    /**
    -0.68
    QMetaType
    -0.66
     ſind
    -0.65
    İstin
    -0.64
     iſt
    -0.64
    ſehen
    -0.63
    ſcher
    -0.62
    POSITIVE LOGITS
     primarily
    0.39
     familiarity
    0.36
    <?
    0.35
     familiar
    0.34
    <!--
    0.33
    FormTagHelper
    0.33
     technically
    0.32
     across
    0.32
     solely
    0.32
     platform
    0.31
    Act Density 0.058%

    No Known Activations