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

    Neuronpedia

    INDEX
    Explanations

    pronouns that indicate personal or group identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itable
    -0.14
     идеÑĤ
    -0.14
     ÐĿаÑģ
    -0.14
     ill
    -0.14
    :numel
    -0.13
    ëĵ±
    -0.13
    _INLINE
    -0.13
    á»ĥ
    -0.13
    Invocation
    -0.13
    _SYM
    -0.13
    POSITIVE LOGITS
     absolutely
    0.23
     exactly
    0.22
     definitely
    0.21
     really
    0.20
     actually
    0.20
     totally
    0.19
     completely
    0.19
    actually
    0.18
    really
    0.16
    -know
    0.15
    Act Density 0.000%

    No Known Activations