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

    Neuronpedia

    INDEX
    Explanations

    the word "for" and its various contexts

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

    conditions with "for"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cantara
    -0.39
    makeConstraints
    -0.36
     themſelves
    -0.36
    lapsingToolbar
    -0.35
    hogany
    -0.35
     Tiong
    -0.35
     explosión
    -0.35
     fumée
    -0.35
    Explo
    -0.34
     pleaſure
    -0.34
    POSITIVE LOGITS
     ligiloj
    0.68
     Infórmanos
    0.66
    rrggbb
    0.61
    對於
    0.57
     '\\;'
    0.54
    对于
    0.53
     betweenstory
    0.52
    fromnode
    0.52
     ARY
    0.52
    WaitGroup
    0.51
    Act Density 0.201%

    No Known Activations