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

    Neuronpedia

    INDEX
    Explanations

    statements about similarity and recurring themes in contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TZ
    -0.14
    foy
    -0.14
     Authority
    -0.13
    undler
    -0.13
    pekt
    -0.13
     nghiá»ĩp
    -0.13
    åĬ
    -0.13
    ahun
    -0.13
    itos
    -0.13
    mobx
    -0.13
    POSITIVE LOGITS
     true
    0.78
    true
    0.67
     True
    0.64
    True
    0.58
     TRUE
    0.55
    	true
    0.49
    _true
    0.49
    .true
    0.46
    TRUE
    0.46
    (true
    0.44
    Act Density 0.030%

    No Known Activations