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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "with" and its variations indicating collaboration or association

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

    together with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SharedCtor
    -0.44
     recipes
    -0.39
    whom
    -0.38
    ReusableCell
    -0.37
    Související
    -0.37
    AccessorTable
    -0.36
    achute
    -0.35
     kyse
    -0.35
     الرياضيه
    -0.35
    msgTypes
    -0.35
    POSITIVE LOGITS
    GIVEREF
    0.56
    EDEFAULT
    0.52
    sieme
    0.52
     tillsammans
    0.50
     همراه
    0.50
    hdessä
    0.50
    Alongside
    0.48
     junto
    0.48
    RTLU
    0.48
     Samen
    0.47
    Act Density 0.114%

    No Known Activations