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

    Neuronpedia

    INDEX
    Explanations

    phrases or constructions involving the words "going to" and their variations

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

    going to be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    حياته
    -0.40
     traces
    -0.39
    RTLU
    -0.39
     armor
    -0.37
    mení
    -0.36
     slu
    -0.34
     handler
    -0.34
     creeps
    -0.34
     creep
    -0.34
    Dtor
    -0.34
    POSITIVE LOGITS
    styleable
    0.54
    Intended
    0.52
     voulais
    0.51
    SequentialGroup
    0.50
    apunov
    0.49
    ReusableCell
    0.49
     uſed
    0.48
     intended
    0.47
    paravant
    0.46
    Originally
    0.46
    Act Density 0.010%

    No Known Activations