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

    Neuronpedia

    INDEX
    Explanations

    the presence of phrases that imply collaborative or supportive actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etten
    -0.16
    occo
    -0.15
    haps
    -0.15
    nesty
    -0.14
    zed
    -0.14
    ichel
    -0.14
    uren
    -0.14
    otal
    -0.14
    acle
    -0.14
    igion
    -0.13
    POSITIVE LOGITS
     regard
    0.34
    stood
    0.32
     regards
    0.30
    standing
    0.29
    /by
    0.26
    holds
    0.25
     respect
    0.24
    drawing
    0.24
     nhau
    0.23
    holding
    0.21
    Act Density 0.511%

    No Known Activations