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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of friendship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.09
    2:0.08
    3:0.09
    4:0.09
    5:0.08
    6:0.08
    7:0.08
    8:0.07
    9:0.07
    10:0.06
    11:0.08
    Negative Logits
    ealous
    -2.65
    successfully
    -2.60
     Guer
    -2.58
    oba
    -2.58
     Parables
    -2.52
    verages
    -2.49
    Brew
    -2.49
    ograp
    -2.48
    gun
    -2.42
    将
    -2.40
    POSITIVE LOGITS
     colonization
    3.11
     linkage
    2.84
     juven
    2.74
     genetics
    2.58
     microbiota
    2.57
    onomic
    2.55
     transporter
    2.54
     terrestrial
    2.54
     neural
    2.50
     containment
    2.48
    Act Density 0.000%

    No Known Activations