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

    Neuronpedia

    INDEX
    Explanations

    negative constructions regarding abilities and past actions

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

    negations ending in 't

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tomas
    -0.39
     jok
    -0.36
    multicolumn
    -0.35
    УДК
    -0.34
     successes
    -0.33
    mannschaft
    -0.33
     advantage
    -0.32
     Trink
    -0.32
     Tomás
    -0.32
    sphase
    -0.31
    POSITIVE LOGITS
     Paglinawan
    0.71
     Signalez
    0.68
    tagHelperRunner
    0.63
     informée
    0.61
     متحده
    0.60
    DataAnnotations
    0.59
    省市镇
    0.59
    SequentialGroup
    0.58
    RefNanny
    0.57
    ⟬
    0.57
    Act Density 0.063%

    No Known Activations