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

    Neuronpedia

    INDEX
    Explanations

    formal terminology related to organizational membership and criteria

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onas
    -0.16
    lediÄŁi
    -0.15
     Decompiled
    -0.15
    åĽº
    -0.14
    èĩ£
    -0.14
    adena
    -0.14
    arel
    -0.14
     CALLBACK
    -0.13
    avl
    -0.13
    aida
    -0.13
    POSITIVE LOGITS
     membership
    0.27
    membership
    0.26
     Membership
    0.24
    Membership
    0.23
    _membership
    0.19
     member
    0.19
     memberships
    0.18
    -members
    0.18
    member
    0.17
    .member
    0.16
    Act Density 0.033%

    No Known Activations