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

    Neuronpedia

    INDEX
    Explanations

    the preposition "to" and its variations

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

    making comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     didst
    -0.58
     canst
    -0.56
    Hentet
    -0.51
    newnode
    -0.49
     pleaſure
    -0.49
    expandindo
    -0.48
    ſelf
    -0.46
     itſelf
    -0.46
    ResponseWriter
    -0.45
     lyre
    -0.45
    POSITIVE LOGITS
     dibanding
    0.67
     THAN
    0.64
     versus
    0.63
    THAN
    0.62
    hdashline
    0.60
     than
    0.60
     Versus
    0.59
    Versus
    0.58
     comparing
    0.58
     compared
    0.57
    Act Density 0.025%

    No Known Activations