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

    Neuronpedia

    INDEX
    Explanations

    phrases related to deception or hidden motives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.02
    2:0.09
    3:0.17
    4:0.09
    5:0.04
    6:0.06
    7:0.04
    8:0.04
    9:0.07
    10:0.14
    11:0.13
    Negative Logits
     juven
    -1.34
     inexperienced
    -1.31
     depreciation
    -1.29
     inver
    -1.27
     ejac
    -1.25
     isot
    -1.19
     inexper
    -1.18
     athlet
    -1.18
     outright
    -1.16
     disposition
    -1.16
    POSITIVE LOGITS
    ');
    1.51
    ';
    1.37
    ').
    1.35
    ffic
    1.29
    BLIC
    1.29
    united
    1.27
    "}],"
    1.25
    thouse
    1.24
    icates
    1.23
    official
    1.21
    Act Density 0.000%

    No Known Activations