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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social interactions and their dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amina
    -0.18
    ewater
    -0.18
    foy
    -0.17
    vrier
    -0.17
    atem
    -0.16
    ickey
    -0.16
    !=(
    -0.15
    Messenger
    -0.15
    kola
    -0.15
    ãĤ¤ãĤº
    -0.15
    POSITIVE LOGITS
    istani
    0.17
    finder
    0.15
    mpp
    0.14
    rien
    0.14
     Ellis
    0.14
    nehmen
    0.14
    mand
    0.14
    nal
    0.14
    EC
    0.14
     Fa
    0.13
    Act Density 0.005%

    No Known Activations