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

    Neuronpedia

    INDEX
    Explanations

    phrases that express continuity or the presence of constant elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aye
    -0.73
    anium
    -0.72
    idas
    -0.71
    dm
    -0.69
    éĥ
    -0.65
    intosh
    -0.65
    doms
    -0.63
    buster
    -0.61
    /#
    -0.60
    chi
    -0.60
    POSITIVE LOGITS
     temptation
    0.88
     lurking
    0.85
     surprises
    0.76
    entimes
    0.72
     exceptions
    0.72
    ounters
    0.71
    olini
    0.70
     hindsight
    0.68
     somebody
    0.68
     gotta
    0.67
    Act Density 0.021%

    No Known Activations