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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and words related to cumulative or additive statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sibling
    -0.14
     widths
    -0.14
    asma
    -0.14
    foy
    -0.14
    fad
    -0.14
    ially
    -0.14
     individuals
    -0.14
    è©
    -0.13
    ortion
    -0.13
    aeper
    -0.13
    POSITIVE LOGITS
     own
    0.30
     ability
    0.24
     theirs
    0.22
     arsenal
    0.21
     sense
    0.21
     abilities
    0.20
     ours
    0.20
     approach
    0.20
     surroundings
    0.19
    mine
    0.19
    Act Density 0.202%

    No Known Activations