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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social roles and family dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elah
    -0.13
    avn
    -0.13
    oref
    -0.12
    ì°®
    -0.12
    obuf
    -0.12
    addtogroup
    -0.12
     azal
    -0.11
    draul
    -0.11
    erule
    -0.11
    alloca
    -0.11
    POSITIVE LOGITS
     at
    1.36
     tại
    0.80
    _at
    0.77
    	at
    0.73
    at
    0.69
    èĩ³å°ij
    0.68
    At
    0.65
    .at
    0.64
    -at
    0.64
     At
    0.62
    Act Density 4.794%

    No Known Activations