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

    Neuronpedia

    INDEX
    Explanations

    phrases related to strengthening or empowerment

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "strength" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    doms
    -0.70
     GEAR
    -0.70
     ult
    -0.63
    ION
    -0.63
    NESS
    -0.61
    LESS
    -0.60
     Blueprint
    -0.58
     trapping
    -0.57
    ãĤ¨ãĥ«
    -0.57
    ãĥ¼ãĥĨãĤ£
    -0.57
    POSITIVE LOGITS
    ng
    1.18
    ller
    1.15
    lla
    1.14
    aks
    1.13
    tti
    1.12
    aky
    1.11
    wn
    1.10
    aking
    1.09
    akable
    1.08
    aked
    1.07
    Act Density 0.026%

    No Known Activations