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

    Neuronpedia

    INDEX
    Explanations

    phrases related to politics and social issues

    oai_token-act-pair · gpt-3.5-turbo

    repeated conjunctions or phrases indicating connection or continuation in discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ":""},{"
    -0.62
    éŃĶ
    -0.59
    :(
    -0.58
    è»
    -0.57
    :[
    -0.56
    uta
    -0.55
    æĥ
    -0.55
    IRT
    -0.54
    atten
    -0.53
    Versions
    -0.52
    POSITIVE LOGITS
     consequently
    0.92
    rogens
    0.88
     therefore
    0.88
     thus
    0.85
    rogen
    0.85
     hence
    0.82
     then
    0.79
     possibly
    0.77
     thereby
    0.76
    romeda
    0.74
    Act Density 0.755%

    No Known Activations